av_lord_ml-Copy1



In [1]:
%load_ext autoreload
%autoreload 2
%matplotlib inline
import  pandas  as  pd 
import  numpy  as  np 
import  matplotlib.pyplot  as  plt 
import  seaborn  as  sns
from  sklearn.model_selection  import  train_test_split
from  sklearn.metrics  import  mean_squared_error
from  sklearn.preprocessing  import  StandardScaler 
from  sklearn.model_selection  import  GridSearchCV
from  sklearn.linear_model  import LinearRegression
from  sklearn.neighbors  import KNeighborsRegressor 
from  sklearn.ensemble  import RandomForestRegressor 
from  sklearn.ensemble  import GradientBoostingRegressor 
from  sklearn.ensemble  import AdaBoostRegressor 
from  sklearn.svm  import LinearSVR
from  sklearn.learning_curve  import  learning_curve
from  scipy  import  stats
from nltk.corpus import stopwords


C:\ProgramData\Anaconda3\lib\site-packages\sklearn\cross_validation.py:41: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
  "This module will be removed in 0.20.", DeprecationWarning)
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\learning_curve.py:22: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the functions are moved. This module will be removed in 0.20
  DeprecationWarning)

In [2]:
from fastai.imports import *
from fastai.structured import *

from pandas_summary import DataFrameSummary
from sklearn.ensemble import RandomForestRegressor, RandomForestClassifier
from IPython.display import display

from sklearn import metrics

In [3]:
PATH = os.getcwd();
PATH = PATH+"\\AV_Lord\\"

In [4]:
!dir {PATH}


 Volume in drive D is Local Disk
 Volume Serial Number is B408-A348

 Directory of D:\Github\fastai\courses\ml1\AV_Lord

25-Mar-18  12:42 AM    <DIR>          .
25-Mar-18  12:42 AM    <DIR>          ..
24-Mar-18  04:08 PM    <DIR>          .ipynb_checkpoints
24-Mar-18  06:53 PM        11,247,959 av_cat_2.csv
23-Mar-18  04:40 PM            58,415 campaign_data.csv
24-Mar-18  04:35 PM     1,382,961,456 combined.raw
25-Mar-18  09:23 AM        24,181,026 logistic_reg_sub2.csv
25-Mar-18  12:42 AM         3,748,609 logistic_reg_sub2.zip
24-Mar-18  12:07 AM         9,700,243 sample_submission.csv
23-Mar-18  04:42 PM        28,686,790 test_BDIfz5B.csv
23-Mar-18  07:55 PM        42,036,287 train.csv
               8 File(s)  1,502,620,785 bytes
               3 Dir(s)  168,866,631,680 bytes free

In [5]:
df_raw = pd.read_csv(f'{PATH}train.csv',low_memory=False)

In [24]:
camp = pd.read_csv(f'{PATH}campaign_data.csv',low_memory=False)

In [25]:
df_raw.shape, camp.shape


Out[25]:
((1023191, 6), (52, 9))

In [26]:
df_raw.get_ftype_counts(),\
camp.get_ftype_counts()


Out[26]:
(int64:dense     4
 object:dense    2
 dtype: int64, int64:dense     5
 object:dense    4
 dtype: int64)

In [27]:
def display_all(df):
    with pd.option_context("display.max_rows", 1000): 
        with pd.option_context("display.max_columns", 1000): 
            display(df)

In [28]:
camp.head(2)


Out[28]:
campaign_id communication_type total_links no_of_internal_links no_of_images no_of_sections email_body subject email_url
0 29 Newsletter 67 61 12 3 Dear AVians,\r\n \r\nWe are shaping up a super... Sneak Peek: A look at the emerging data scienc... http://r.newsletters.analyticsvidhya.com/7um44...
1 30 Upcoming Events 18 14 7 1 Dear AVians,\r\n \r\nAre your eager to know wh... [July] Data Science Expert Meetups & Competiti... http://r.newsletters.analyticsvidhya.com/7up0e...

In [ ]:
df[col].apply(lambda x: len(str(x).split(" "))#word count
              
df[col].str.len()#char count
              
def avg_word(sentence):
  words = sentence.split()
  return (sum(len(word) for word in words)/len(words))
df['avg_word'] = df[col].apply(lambda x: avg_word(x))
              
stop = stopwords.words('english')
df['stopwords'] = df['tweet'].apply(lambda x: len([x for x in x.split() if x in stop]))

df['upper'] = df['tweet'].apply(lambda x: len([x for x in x.split() if x.isupper()]))
df[col] = df[col].apply(lamda x: " ".join(x.lower() for x in split()))
df['removal_of_stopwords'] = df['tweet'].apply(lambda x: " ".join(x for x in x.split() if x not in stop))

In [21]:
freq = pd.Series(' '.join(camp['email_body']).split()).value_counts()[:10]
freq = list(freq.index)
camp['email_body'] = camp['email_body'].apply(lambda x: " ".join(x for x in x.split() if x not in freq))
camp['email_body'].head()

freq = pd.Series(' '.join(camp['email_body']).split()).value_counts()[-10:]
freq = list(freq.index)
camp['email_body'] = camp['email_body'].apply(lambda x: " ".join(x for x in x.split() if x not in freq))
camp['email_body'].head()


Out[21]:
0    Dear AVians, We are shaping up superb science ...
1    Dear AVians, Are your eager know what are upco...
2    Early Bird Pricing Till August 07 – Save upto ...
3    Hi ? Before I dive into why should attend this...
4    Fireside Chat with DJ Patil - master is here! ...
Name: email_body, dtype: object

In [ ]:


In [ ]:


In [ ]:


In [11]:
camp['communication_type'].value_counts().plot(kind='barh');



In [28]:
print(df_raw.is_open.value_counts())
df_raw['is_open'].value_counts().plot(kind='bar')


0    920401
1    102790
Name: is_open, dtype: int64
Out[28]:
<matplotlib.axes._subplots.AxesSubplot at 0x19fa3c8c9b0>

In [37]:
add_datepart(df_raw,'send_date')
df_raw.drop('send_Elapsed', axis=1, inplace=True)
df_raw.head(1)


Out[37]:
id user_id campaign_id is_open is_click send_Year send_Month send_Week send_Day send_Dayofweek send_Dayofyear send_Is_month_end send_Is_month_start send_Is_quarter_end send_Is_quarter_start send_Is_year_end send_Is_year_start
0 42_14051 14051 42 0 0 2017 1 2 9 0 9 False False False False False False

In [38]:
train_cats(df_raw)

In [39]:
df_raw['user_id'].value_counts()


Out[39]:
183177    20
145022    20
4118      19
216700    19
114180    19
197188    19
47152     19
163618    18
69970     18
196296    18
122065    18
218458    18
114075    18
38127     18
162109    18
67867     18
163399    18
156029    18
157374    18
36788     18
92799     18
49136     18
28463     18
160443    18
117705    18
86941     18
152991    18
143179    18
185773    18
111959    18
          ..
9258       1
1070       1
146480     1
60010      1
39524      1
48059      1
43618      1
156523     1
23463      1
21414      1
37685      1
230364     1
17199      1
134125     1
170356     1
182903     1
190842     1
178809     1
124304     1
85381      1
97281      1
171007     1
78593      1
228376     1
173048     1
185334     1
181236     1
2854       1
138223     1
188649     1
Name: user_id, Length: 168236, dtype: int64

In [40]:
df_raw['campaign_id'].value_counts().plot(kind='barh');



In [42]:
df_raw.get_ftype_counts()


Out[42]:
bool:dense         6
category:dense     1
int64:dense       10
dtype: int64

In [ ]:
df_raw['send_Month'].value_counts().plot(kind='bar')

In [43]:
df_raw.groupby('campaign_id')['is_click'].describe()


Out[43]:
count mean std min 25% 50% 75% max
campaign_id
29 69129.0 0.016549 0.127574 0.0 0.0 0.0 0.0 1.0
30 69756.0 0.012615 0.111608 0.0 0.0 0.0 0.0 1.0
31 3192.0 0.024436 0.154423 0.0 0.0 0.0 0.0 1.0
32 69624.0 0.010600 0.102409 0.0 0.0 0.0 0.0 1.0
33 46815.0 0.011449 0.106388 0.0 0.0 0.0 0.0 1.0
34 73112.0 0.009807 0.098544 0.0 0.0 0.0 0.0 1.0
35 4121.0 0.043921 0.204945 0.0 0.0 0.0 0.0 1.0
36 73415.0 0.004767 0.068882 0.0 0.0 0.0 0.0 1.0
37 7559.0 0.006482 0.080257 0.0 0.0 0.0 0.0 1.0
38 7232.0 0.007605 0.086881 0.0 0.0 0.0 0.0 1.0
39 3487.0 0.046171 0.209886 0.0 0.0 0.0 0.0 1.0
40 4822.0 0.012028 0.109023 0.0 0.0 0.0 0.0 1.0
41 2786.0 0.014716 0.120437 0.0 0.0 0.0 0.0 1.0
42 81253.0 0.012824 0.112516 0.0 0.0 0.0 0.0 1.0
43 67.0 0.029851 0.171460 0.0 0.0 0.0 0.0 1.0
44 39498.0 0.011697 0.107519 0.0 0.0 0.0 0.0 1.0
45 5322.0 0.071402 0.257519 0.0 0.0 0.0 0.0 1.0
46 9831.0 0.027566 0.163734 0.0 0.0 0.0 0.0 1.0
47 14230.0 0.016725 0.128244 0.0 0.0 0.0 0.0 1.0
48 51456.0 0.012166 0.109626 0.0 0.0 0.0 0.0 1.0
49 81358.0 0.012758 0.112231 0.0 0.0 0.0 0.0 1.0
50 39710.0 0.014455 0.119358 0.0 0.0 0.0 0.0 1.0
51 3882.0 0.043792 0.204658 0.0 0.0 0.0 0.0 1.0
52 82160.0 0.014192 0.118282 0.0 0.0 0.0 0.0 1.0
53 85431.0 0.010090 0.099942 0.0 0.0 0.0 0.0 1.0
54 93943.0 0.010251 0.100727 0.0 0.0 0.0 0.0 1.0

In [95]:
df_raw['send_Day'].value_counts().plot(kind='bar')


Out[95]:
<matplotlib.axes._subplots.AxesSubplot at 0x1eb80fbca58>

In [134]:
def code(url): return re.split('/', url)[3][:11]
def lexical_diversity(my_text_data):
    word_count = len(my_text_data)
    vocab_size = len(set(my_text_data))
    diversity_score = vocab_size / word_count
    return diversity_score

In [137]:
## Add features on camp df
camp['len_email_body'] = len(camp['email_body'])
camp['diversity_email_body'] = camp['email_body'].apply(lexical_diversity)
camp['diversity_subject'] = camp['subject'].apply(lexical_diversity)
camp['diversity_email_url'] = camp['email_url'].apply(lexical_diversity)
camp['body_per_sec'] = camp['len_email_body']/camp['no_of_sections']
camp['links_per_sec'] = camp['total_links']/camp['no_of_sections']
camp['img_per_sec'] = camp['no_of_images']/ camp['no_of_sections']
camp['code_email_url'] = camp['email_url'].apply(code)
camp['other_links'] = camp['total_links'] - camp['no_of_internal_links']
camp['av_links_percent'] = camp['no_of_internal_links'] / camp['total_links']

In [142]:
camp.drop(['email_body','email_url','subject'], axis=1,inplace=True)

In [ ]:
camp = pd.get_dummies(camp);camp.head(2)

In [154]:
df_raw = df_raw.merge(camp,on='campaign_id');
df_raw.head(1)


Out[154]:
id user_id campaign_id is_open is_click send_Year send_Month send_Week send_Day send_Dayofweek ... code_email_url_7wra6vb5p4c code_email_url_7wrjo7b5p4c code_email_url_7ww0uvb5p4c code_email_url_7wx2s7b5p4c code_email_url_7wxlqvb5p4c code_email_url_7wxv87b5p4c code_email_url_7wz6mvb5p4c code_email_url_7wzpljb5p4c code_email_url_7x08k7b5p4c code_email_url_o7ohwml8lxh
0 42_14051 14051 42 0 0 2017 1 2 9 0 ... 0 0 0 0 0 0 0 0 0 0

1 rows × 89 columns


In [159]:
len(np.unique(df_raw['user_id']))


Out[159]:
168236

In [164]:
test.head(1)


Out[164]:
id campaign_id user_id send_Year send_Month send_Week send_Day send_Dayofweek send_Dayofyear send_Is_month_end send_Is_month_start send_Is_quarter_end send_Is_quarter_start send_Is_year_end send_Is_year_start
0 63_122715 63 122715 2018 1 1 2 1 2 False False False False False False

In [67]:
df_raw.drop(['user_id', 'campaign_id'], axis=1, inplace=True);
df_raw.get_ftype_counts()


Out[67]:
int32:dense      6
int64:dense     12
object:dense     2
dtype: int64

In [88]:
for s in np.unique(df_raw['communication_type']): 
    print ( s ,  '->' ,  hash ( s ) % 9)


Conference -> 8
Corporate -> 7
Hackathon -> 4
Newsletter -> 1
Others -> 5
Upcoming Events -> 0
Webinar -> 6

In [94]:
sns.set()
corr_matrix = df_raw.corr () 
plt.figure(figsize=(10,10))
sns.heatmap(corr_matrix , annot = True , fmt  =  ".2f" , cbar  =  True , cmap = 'PuOr');


Out[94]:
<matplotlib.axes._subplots.AxesSubplot at 0x1eb8b966fd0>

df_raw['start_month'] = df_raw['send_Year']*100 + df_raw['send_Month'] df_raw['noon'] = np.where(np.logical_and(df_raw['start_hour']>11 , df_raw['start_hour']<=19),1,0) df_raw['night'] = np.where(np.logical_and(df_raw['start_hour']>19, df_raw['start_hour']<24),1,0)

span_time = pd.concat([time_df['seconds'], time_df_test['seconds']]) df_raw['session_span'] = span_time

df_raw['session_span_per_n_uniques_sites'] = df_raw['session_span']/df_raw['n_unique_sites']

df_raw['hour_sin_x'] = df_raw['start_hour'].apply(lambda ts: np.sin(2pits/24.)) df_raw['hour_cos_x'] = df_raw['start_hour'].apply(lambda ts: np.cos(2pits/24.))""


In [175]:
y_target = df_raw['is_click'];
df_raw.head(1).T


Out[175]:
0
id 42_14051
user_id 14051
campaign_id 42
is_open 0
is_click 0
send_Year 2017
send_Month 1
send_Week 2
send_Day 9
send_Dayofweek 0
send_Dayofyear 9
send_Is_month_end False
send_Is_month_start False
send_Is_quarter_end False
send_Is_quarter_start False
send_Is_year_end False
send_Is_year_start False
total_links 88
no_of_internal_links 79
no_of_images 13
no_of_sections 4
len_email_body 52
diversity_email_body 0.0419682
diversity_subject 0.386364
body_per_sec 13
diversity_email_url 0.457143
img_per_sec 3.25
other_links 9
av_links_percent 0.897727
links_per_sec 22
... ...
code_email_url_7vtb2vb5p4c 0
code_email_url_7vv5g7b5p4c 0
code_email_url_7vzmmvb5p4c 0
code_email_url_7w2sevb5p4c 0
code_email_url_7w3uc7b5p4c 0
code_email_url_7w43tjb5p4c 0
code_email_url_7w5y6vb5p4c 0
code_email_url_7w6qmvb5p4c 0
code_email_url_7w7047b5p4c 0
code_email_url_7wghg7b5p4c 0
code_email_url_7wh9w7b5p4c 0
code_email_url_7whsuvb5p4c 0
code_email_url_7wjn87b5p4c 0
code_email_url_7wjwpjb5p4c 0
code_email_url_7wkfo7b5p4c 0
code_email_url_7wnbyvb5p4c 0
code_email_url_7wo4evb5p4c 0
code_email_url_7wowuvb5p4c 0
code_email_url_7wppavb5p4c 0
code_email_url_7wqhqvb5p4c 0
code_email_url_7wra6vb5p4c 0
code_email_url_7wrjo7b5p4c 0
code_email_url_7ww0uvb5p4c 0
code_email_url_7wx2s7b5p4c 0
code_email_url_7wxlqvb5p4c 0
code_email_url_7wxv87b5p4c 0
code_email_url_7wz6mvb5p4c 0
code_email_url_7wzpljb5p4c 0
code_email_url_7x08k7b5p4c 0
code_email_url_o7ohwml8lxh 0

89 rows × 1 columns


In [176]:
os.makedirs('tmp', exist_ok=True)
df_raw.to_feather('tmp/av_lord-raw')

In [29]:
df_raw = pd.read_feather('tmp/av_lord-raw')

In [134]:
df, y, nas, mapper = proc_df(df_raw, 'is_click', do_scale=True,max_n_cat=30)

In [135]:
sns.countplot(y)


Out[135]:
<matplotlib.axes._subplots.AxesSubplot at 0x27193e5ff28>

In [139]:
y[-26:] = 0

In [229]:
#df.drop('is_open', axis=1, inplace=True)
m = RandomForestRegressor(n_jobs=-1)
m.fit(df, y)
m.score(df,y)


Out[229]:
0.7547053047196518

In [141]:
def print_score(m):
    res = [rmse(m.predict(X_train), y_train), rmse(m.predict(X_valid), y_valid),
                m.score(X_train, y_train), m.score(X_valid, y_valid)]
    if hasattr(m, 'oob_score_'): res.append(m.oob_score_)
    print(res)

In [ ]:
m = RandomForestRegressor(n_jobs=-1)
%%time m.fit(X_train, y_train)
print_score(m)

In [42]:
display_all(df_raw.isnull().sum().sort_index()/len(df_raw))


campaign_id              0.0
id                       0.0
is_click                 0.0
is_open                  0.0
send_Day                 0.0
send_Dayofweek           0.0
send_Dayofyear           0.0
send_Is_month_end        0.0
send_Is_month_start      0.0
send_Is_quarter_end      0.0
send_Is_quarter_start    0.0
send_Is_year_end         0.0
send_Is_year_start       0.0
send_Month               0.0
send_Week                0.0
send_Year                0.0
user_id                  0.0
dtype: float64

In [178]:
display_all(df.columns)


Index(['id', 'user_id', 'campaign_id', 'send_Year', 'send_Month', 'send_Week',
       'send_Day', 'send_Dayofweek', 'send_Dayofyear', 'total_links',
       'no_of_internal_links', 'no_of_images', 'no_of_sections', 'email_body',
       'subject', 'email_url', 'link_diff', 'img_per_sec', 'link_diff_%',
       'img_per_section', 'user_id_na', 'is_open_na', 'send_Year_na',
       'send_Month_na', 'send_Week_na', 'send_Day_na', 'send_Dayofweek_na',
       'send_Dayofyear_na', 'send_Is_month_end_0.0', 'send_Is_month_end_nan',
       'send_Is_month_start_0.0', 'send_Is_month_start_nan',
       'send_Is_quarter_end_0.0', 'send_Is_quarter_end_nan',
       'send_Is_quarter_start_0.0', 'send_Is_quarter_start_nan',
       'send_Is_year_end_0.0', 'send_Is_year_end_nan',
       'send_Is_year_start_0.0', 'send_Is_year_start_nan',
       'communication_type_Conference', 'communication_type_Corporate',
       'communication_type_Hackathon', 'communication_type_Newsletter',
       'communication_type_Others', 'communication_type_Upcoming Events',
       'communication_type_Webinar', 'communication_type_nan', 'av_links'],
      dtype='object')

In [ ]:

testset transforms


In [33]:
test = pd.read_csv(f'{PATH}\\test_BDIfz5B.csv')

In [34]:
test.shape


Out[34]:
(773858, 4)

In [35]:
test.head(2)


Out[35]:
id campaign_id user_id send_date
0 63_122715 63 122715 01-02-2018 22:35
1 56_76206 56 76206 02-01-2018 08:15

In [45]:
add_datepart(test,'send_date');
test.drop('send_Elapsed',axis= 1, inplace=True)

In [46]:
test = test * 1
train_cats(test)

In [47]:
test = test.merge(camp,on='campaign_id');

In [134]:
test.drop(['user_id', 'campaign_id'], axis=1, inplace=True);
test['communication_type'] = mapped;
test.get_ftype_counts()


Out[134]:
bool:dense         6
category:dense     1
int64:dense       10
object:dense       1
dtype: int64

In [137]:
test['link_diff'] = test['total_links'] - test['no_of_internal_links']
test['av_links'] = (test['no_of_internal_links']/ test['total_links'])
test['img_per_section'] = test['no_of_images']/ test['no_of_sections']
test['link_diff_%'] = (test['total_links'] - test['no_of_internal_links'])/test['total_links']
test.head(1)


Out[137]:
id send_Year send_Month send_Week send_Day send_Dayofweek send_Dayofyear send_Is_month_end send_Is_month_start send_Is_quarter_end ... send_Is_year_start communication_type total_links no_of_internal_links no_of_images no_of_sections link_diff av_links img_per_section link_diff_%
0 63_122715 2018 1 1 2 1 2 False False False ... False 3 68 64 15 5 4 0.941176 3.0 0.058824

1 rows × 22 columns


In [138]:
df_raw['link_diff'] = df_raw['total_links'] - df_raw['no_of_internal_links']
df_raw['av_links'] = (df_raw['no_of_internal_links']/ df_raw['total_links'])
df_raw['img_per_section'] = df_raw['no_of_images']/ df_raw['no_of_sections']
df_raw['link_diff_%'] = (df_raw['total_links'] - df_raw['no_of_internal_links'])/df_raw['total_links']
df_raw.head(1)


Out[138]:
id is_open is_click send_Year send_Month send_Week send_Day send_Dayofweek send_Dayofyear send_Is_month_end ... send_Is_year_start communication_type total_links no_of_internal_links no_of_images no_of_sections link_diff av_links img_per_section link_diff_%
0 42_14051 0 0 2017 1 2 9 0 9 0 ... 0 3 88 79 13 4 9 0.897727 3.25 0.102273

1 rows × 24 columns


In [139]:
test.to_feather('tmp/av_lord_test')

In [30]:
test = pd.read_feather('tmp/av_lord_test')

In [31]:
df_raw.head(1)


Out[31]:
id user_id campaign_id is_open is_click send_Year send_Month send_Week send_Day send_Dayofweek ... code_email_url_7wra6vb5p4c code_email_url_7wrjo7b5p4c code_email_url_7ww0uvb5p4c code_email_url_7wx2s7b5p4c code_email_url_7wxlqvb5p4c code_email_url_7wxv87b5p4c code_email_url_7wz6mvb5p4c code_email_url_7wzpljb5p4c code_email_url_7x08k7b5p4c code_email_url_o7ohwml8lxh
0 42_14051 14051 42 0 0 2017 1 2 9 0 ... 0 0 0 0 0 0 0 0 0 0

1 rows × 89 columns


In [32]:
test.head(1)


Out[32]:
id send_Year send_Month send_Week send_Day send_Dayofweek send_Dayofyear send_Is_month_end send_Is_month_start send_Is_quarter_end ... send_Is_year_start communication_type total_links no_of_internal_links no_of_images no_of_sections link_diff av_links img_per_section link_diff_%
0 63_122715 2018 1 1 2 1 2 False False False ... False 3 68 64 15 5 4 0.941176 3.0 0.058824

1 rows × 22 columns

Rough


In [218]:
test, _, _ = proc_df(test,max_n_cat=30,mapper=mapper,na_dict=nas)

In [219]:
test.columns


Out[219]:
Index(['id', 'campaign_id', 'user_id', 'y', 'send_Year', 'send_Month',
       'send_Week', 'send_Day', 'send_Dayofweek', 'send_Dayofyear',
       ...
       'email_url_http://r.newsletters.analyticsvidhya.com/7wra6vb5p4c.html?t=1520942329',
       'email_url_http://r.newsletters.analyticsvidhya.com/7wrjo7b5p4c.html?t=1520942329',
       'email_url_http://r.newsletters.analyticsvidhya.com/7ww0uvb5p4c.html?t=1520940826',
       'email_url_http://r.newsletters.analyticsvidhya.com/7wx2s7b5p4c.html?t=1520940826',
       'email_url_http://r.newsletters.analyticsvidhya.com/7wxlqvb5p4c.html?t=1520940826',
       'email_url_http://r.newsletters.analyticsvidhya.com/7wxv87b5p4c.html?t=1520940826',
       'email_url_http://r.newsletters.analyticsvidhya.com/7wz6mvb5p4c.html?t=1520940826',
       'email_url_http://r.newsletters.analyticsvidhya.com/7wzpljb5p4c.html?t=1520935115',
       'email_url_http://r.newsletters.analyticsvidhya.com/7x08k7b5p4c.html?t=1520935115',
       'email_url_nan'],
      dtype='object', length=113)

In [224]:
df.drop(list(set(df.columns) - set(test.columns)), axis=1,inplace=True)

In [228]:
len(test.columns)


Out[228]:
29

In [227]:
len(df.columns)


Out[227]:
29

In [51]:
print(df['img_per_sec'].value_counts())
sns.countplot(df['img_per_sec'],orient='h');


2.000000     211722
7.000000     139380
3.000000     132195
13.000000     85433
2.500000      82163
16.000000     81358
3.250000      81253
4.000000      76361
1.000000      50942
2.833333      39710
3.166667      39498
5.000000       3198
3.750000          2
3.500000          1
9.000000          1
Name: img_per_sec, dtype: int64

In [43]:
print(df['is_open'].value_counts())
sns.countplot(df['is_open']);


0.0    920401
1.0    102790
Name: is_open, dtype: int64

In [38]:
sns.countplot(df['no_of_images']);



In [39]:
sns.countplot(df['no_of_sections']);



In [37]:
sns.countplot(df['link_diff']);


Out[37]:
<matplotlib.axes._subplots.AxesSubplot at 0x1f117841a20>

In [81]:
train_cats(df)

In [82]:
apply_cats(test, df)

In [87]:
df.drop(['id', 'user_id'], axis=1, inplace=True);
test.drop(['id', 'user_id'], axis=1, inplace=True);

In [88]:
df.head(1)


Out[88]:
campaign_id send_Year send_Month send_Week send_Day send_Dayofweek send_Dayofyear send_Is_month_end send_Is_month_start send_Is_quarter_end ... no_of_internal_links no_of_images no_of_sections email_body subject email_url link_diff link_diff_% img_per_section av_links
0 42 2017.0 1.0 2.0 9.0 0.0 9.0 False False False ... 79 13 4 September Newsletter\r\n \r\nDear AVians,\r\n ... [September] Exciting days ahead with DataHack ... http://r.newsletters.analyticsvidhya.com/7v3rd... 9 10.227273 3.25 89.772727

1 rows × 25 columns


In [89]:
test.head(1)


Out[89]:
campaign_id send_Year send_Month send_Week send_Day send_Dayofweek send_Dayofyear send_Is_month_end send_Is_month_start send_Is_quarter_end ... no_of_internal_links no_of_images no_of_sections email_body subject email_url link_diff av_links img_per_section link_diff_%
0 63 2018 1 1 2 1 2 False False False ... 64 15 5 \r\nFebruary 2018 Newsletter\r\n \r\nDear AVia... AVbytes, Ultimate 2018 learning path and aweso... http://r.newsletters.analyticsvidhya.com/7whsu... 4 94.117647 3.0 5.882353

1 rows × 25 columns


In [90]:
df.info()


<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1023217 entries, 0 to 1023216
Data columns (total 25 columns):
campaign_id              1023217 non-null int64
send_Year                1023191 non-null float64
send_Month               1023191 non-null float64
send_Week                1023191 non-null float64
send_Day                 1023191 non-null float64
send_Dayofweek           1023191 non-null float64
send_Dayofyear           1023191 non-null float64
send_Is_month_end        1023191 non-null category
send_Is_month_start      1023191 non-null category
send_Is_quarter_end      1023191 non-null category
send_Is_quarter_start    1023191 non-null category
send_Is_year_end         1023191 non-null category
send_Is_year_start       1023191 non-null category
communication_type       1023217 non-null category
total_links              1023217 non-null int64
no_of_internal_links     1023217 non-null int64
no_of_images             1023217 non-null int64
no_of_sections           1023217 non-null int64
email_body               1023217 non-null category
subject                  1023217 non-null category
email_url                1023217 non-null category
link_diff                1023217 non-null int64
link_diff_%              1023217 non-null float64
img_per_section          1023217 non-null float64
av_links                 1023217 non-null float64
dtypes: category(10), float64(9), int64(6)
memory usage: 126.9 MB

model


In [177]:
df_raw.get_ftype_counts()


Out[177]:
bool:dense         6
category:dense     1
float64:dense      7
int64:dense       16
uint8:dense       59
dtype: int64

In [180]:
df_raw['comb_id'] = df_raw['user_id']*100+ df_raw['campaign_id'];
test['comb_id'] = test['user_id']*100+ test['campaign_id'];

In [181]:
df_raw.drop(['id','user_id','campaign_id'], axis=1,inplace=True);
test.drop(['id','user_id','campaign_id'], axis=1,inplace=True);

In [186]:
test.head(1)


Out[186]:
send_Year send_Month send_Week send_Day send_Dayofweek send_Dayofyear send_Is_month_end send_Is_month_start send_Is_quarter_end send_Is_quarter_start ... code_email_url_7wrjo7b5p4c code_email_url_7ww0uvb5p4c code_email_url_7wx2s7b5p4c code_email_url_7wxlqvb5p4c code_email_url_7wxv87b5p4c code_email_url_7wz6mvb5p4c code_email_url_7wzpljb5p4c code_email_url_7x08k7b5p4c code_email_url_o7ohwml8lxh comb_id
0 2018 1 1 2 1 2 False False False False ... 0 0 0 0 0 0 0 0 0 12271563

1 rows × 85 columns


In [188]:
df_raw.drop(['is_click'],axis=1,inplace=True)
df_raw.drop('is_open',axis=1,inplace=True)

In [144]:
categorical_features_indices = np.where(df_raw.dtypes == 'category')[0]

In [145]:
categorical_features_indices


Out[145]:
array([], dtype=int64)

In [195]:
def rmse(x,y): return math.sqrt(((x-y)**2).mean())

def print_score(m):
    res = [rmse(m.predict(X_train), y_train), rmse(m.predict(X_valid), y_valid),
                m.score(X_train, y_train), m.score(X_valid, y_valid)]
    if hasattr(m, 'oob_score_'): res.append(m.oob_score_)
    print(res)

In [196]:
from sklearn.model_selection import train_test_split

In [197]:
from sklearn.preprocessing import StandardScaler
df_raw_scaled = StandardScaler().fit_transform(df_raw[:])
test_scaled = StandardScaler().fit_transform(test[:])

In [202]:
X_train, X_validation, y_train, y_validation = train_test_split(df_raw, y_target, train_size=0.8, random_state=17)
lr = LogisticRegression(C=1, random_state=17, solver='lbfgs',class_weight='balanced',n_jobs=-1,max_iter=2000).fit(X_train,y_train)


C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_split.py:2026: FutureWarning: From version 0.21, test_size will always complement train_size unless both are specified.
  FutureWarning)

In [203]:
preds = lr.predict_proba(test_scaled)

In [212]:
#importing library and building model
from catboost import CatBoostClassifier
model=CatBoostClassifier(iterations=1000, depth=10,learning_rate=0.01, loss_function='CrossEntropy')
model.fit(X_train, y_train,eval_set=(X_validation, y_validation))


0:	learn: 0.6718602	test: 0.6718565	best: 0.6718565 (0)	total: 1.35s	remaining: 22m 31s
1:	learn: 0.6513260	test: 0.6513192	best: 0.6513192 (1)	total: 2.24s	remaining: 18m 38s
2:	learn: 0.6314951	test: 0.6314901	best: 0.6314901 (2)	total: 3.39s	remaining: 18m 48s
3:	learn: 0.6124003	test: 0.6123970	best: 0.6123970 (3)	total: 4.46s	remaining: 18m 30s
4:	learn: 0.5937470	test: 0.5937406	best: 0.5937406 (4)	total: 5.64s	remaining: 18m 41s
5:	learn: 0.5757953	test: 0.5757863	best: 0.5757863 (5)	total: 7.12s	remaining: 19m 39s
6:	learn: 0.5584940	test: 0.5584821	best: 0.5584821 (6)	total: 7.94s	remaining: 18m 46s
7:	learn: 0.5416949	test: 0.5416788	best: 0.5416788 (7)	total: 9.58s	remaining: 19m 47s
8:	learn: 0.5255072	test: 0.5254872	best: 0.5254872 (8)	total: 10.8s	remaining: 19m 47s
9:	learn: 0.5099054	test: 0.5098842	best: 0.5098842 (9)	total: 11.7s	remaining: 19m 21s
10:	learn: 0.4948499	test: 0.4948265	best: 0.4948265 (10)	total: 12.7s	remaining: 19m
11:	learn: 0.4802808	test: 0.4802561	best: 0.4802561 (11)	total: 14.3s	remaining: 19m 41s
12:	learn: 0.4662152	test: 0.4661884	best: 0.4661884 (12)	total: 15.9s	remaining: 20m 3s
13:	learn: 0.4525927	test: 0.4525606	best: 0.4525606 (13)	total: 17.7s	remaining: 20m 49s
14:	learn: 0.4394821	test: 0.4394510	best: 0.4394510 (14)	total: 19.2s	remaining: 21m 1s
15:	learn: 0.4269029	test: 0.4268716	best: 0.4268716 (15)	total: 20.7s	remaining: 21m 15s
16:	learn: 0.4147286	test: 0.4146962	best: 0.4146962 (16)	total: 21.7s	remaining: 20m 55s
17:	learn: 0.4029900	test: 0.4029582	best: 0.4029582 (17)	total: 23s	remaining: 20m 52s
18:	learn: 0.3916296	test: 0.3916006	best: 0.3916006 (18)	total: 24.7s	remaining: 21m 15s
19:	learn: 0.3806632	test: 0.3806350	best: 0.3806350 (19)	total: 26.1s	remaining: 21m 16s
20:	learn: 0.3701222	test: 0.3700933	best: 0.3700933 (20)	total: 26.8s	remaining: 20m 51s
21:	learn: 0.3600028	test: 0.3599749	best: 0.3599749 (21)	total: 28.2s	remaining: 20m 52s
22:	learn: 0.3501039	test: 0.3500733	best: 0.3500733 (22)	total: 29.8s	remaining: 21m 3s
23:	learn: 0.3406593	test: 0.3406280	best: 0.3406280 (23)	total: 30.6s	remaining: 20m 43s
24:	learn: 0.3315767	test: 0.3315459	best: 0.3315459 (24)	total: 31.7s	remaining: 20m 36s
25:	learn: 0.3228220	test: 0.3227931	best: 0.3227931 (25)	total: 32.4s	remaining: 20m 14s
26:	learn: 0.3143739	test: 0.3143459	best: 0.3143459 (26)	total: 33.2s	remaining: 19m 56s
27:	learn: 0.3061425	test: 0.3061112	best: 0.3061112 (27)	total: 35s	remaining: 20m 14s
28:	learn: 0.2981844	test: 0.2981527	best: 0.2981527 (28)	total: 36.7s	remaining: 20m 30s
29:	learn: 0.2905096	test: 0.2904769	best: 0.2904769 (29)	total: 38.3s	remaining: 20m 37s
30:	learn: 0.2831044	test: 0.2830699	best: 0.2830699 (30)	total: 39.9s	remaining: 20m 47s
31:	learn: 0.2759891	test: 0.2759550	best: 0.2759550 (31)	total: 41.7s	remaining: 21m 1s
32:	learn: 0.2691229	test: 0.2690896	best: 0.2690896 (32)	total: 43.5s	remaining: 21m 15s
33:	learn: 0.2625235	test: 0.2624918	best: 0.2624918 (33)	total: 45.1s	remaining: 21m 22s
34:	learn: 0.2562166	test: 0.2561863	best: 0.2561863 (34)	total: 45.7s	remaining: 20m 59s
35:	learn: 0.2500796	test: 0.2500493	best: 0.2500493 (35)	total: 47.5s	remaining: 21m 12s
36:	learn: 0.2441620	test: 0.2441315	best: 0.2441315 (36)	total: 48.4s	remaining: 20m 58s
37:	learn: 0.2384901	test: 0.2384609	best: 0.2384609 (37)	total: 49.5s	remaining: 20m 52s
38:	learn: 0.2329866	test: 0.2329589	best: 0.2329589 (38)	total: 50.3s	remaining: 20m 39s
39:	learn: 0.2276662	test: 0.2276380	best: 0.2276380 (39)	total: 51.6s	remaining: 20m 37s
40:	learn: 0.2224945	test: 0.2224652	best: 0.2224652 (40)	total: 53s	remaining: 20m 39s
41:	learn: 0.2175542	test: 0.2175248	best: 0.2175248 (41)	total: 54.4s	remaining: 20m 41s
42:	learn: 0.2127379	test: 0.2127084	best: 0.2127084 (42)	total: 55.9s	remaining: 20m 43s
43:	learn: 0.2081174	test: 0.2080876	best: 0.2080876 (43)	total: 57.6s	remaining: 20m 52s
44:	learn: 0.2036353	test: 0.2036048	best: 0.2036048 (44)	total: 59.3s	remaining: 20m 57s
45:	learn: 0.1993351	test: 0.1993039	best: 0.1993039 (45)	total: 1m 1s	remaining: 21m 8s
46:	learn: 0.1951671	test: 0.1951347	best: 0.1951347 (46)	total: 1m 2s	remaining: 21m 17s
47:	learn: 0.1911797	test: 0.1911474	best: 0.1911474 (47)	total: 1m 4s	remaining: 21m 27s
48:	learn: 0.1872959	test: 0.1872632	best: 0.1872632 (48)	total: 1m 6s	remaining: 21m 31s
49:	learn: 0.1835836	test: 0.1835513	best: 0.1835513 (49)	total: 1m 7s	remaining: 21m 22s
50:	learn: 0.1799605	test: 0.1799275	best: 0.1799275 (50)	total: 1m 8s	remaining: 21m 21s
51:	learn: 0.1764808	test: 0.1764476	best: 0.1764476 (51)	total: 1m 10s	remaining: 21m 29s
52:	learn: 0.1731126	test: 0.1730794	best: 0.1730794 (52)	total: 1m 12s	remaining: 21m 31s
53:	learn: 0.1698672	test: 0.1698343	best: 0.1698343 (53)	total: 1m 13s	remaining: 21m 30s
54:	learn: 0.1667516	test: 0.1667198	best: 0.1667198 (54)	total: 1m 15s	remaining: 21m 36s
55:	learn: 0.1637087	test: 0.1636781	best: 0.1636781 (55)	total: 1m 17s	remaining: 21m 41s
56:	learn: 0.1607666	test: 0.1607359	best: 0.1607359 (56)	total: 1m 18s	remaining: 21m 33s
57:	learn: 0.1579417	test: 0.1579112	best: 0.1579112 (57)	total: 1m 18s	remaining: 21m 23s
58:	learn: 0.1551949	test: 0.1551642	best: 0.1551642 (58)	total: 1m 20s	remaining: 21m 27s
59:	learn: 0.1525670	test: 0.1525368	best: 0.1525368 (59)	total: 1m 21s	remaining: 21m 19s
60:	learn: 0.1500323	test: 0.1500033	best: 0.1500033 (60)	total: 1m 22s	remaining: 21m 9s
61:	learn: 0.1475446	test: 0.1475154	best: 0.1475154 (61)	total: 1m 24s	remaining: 21m 11s
62:	learn: 0.1451684	test: 0.1451403	best: 0.1451403 (62)	total: 1m 24s	remaining: 21m 3s
63:	learn: 0.1428494	test: 0.1428224	best: 0.1428224 (63)	total: 1m 26s	remaining: 20m 59s
64:	learn: 0.1406027	test: 0.1405752	best: 0.1405752 (64)	total: 1m 27s	remaining: 21m 4s
65:	learn: 0.1384244	test: 0.1383969	best: 0.1383969 (65)	total: 1m 29s	remaining: 21m 8s
66:	learn: 0.1363468	test: 0.1363202	best: 0.1363202 (66)	total: 1m 30s	remaining: 21m
67:	learn: 0.1343335	test: 0.1343072	best: 0.1343072 (67)	total: 1m 31s	remaining: 20m 58s
68:	learn: 0.1323514	test: 0.1323247	best: 0.1323247 (68)	total: 1m 33s	remaining: 21m 2s
69:	learn: 0.1304514	test: 0.1304244	best: 0.1304244 (69)	total: 1m 34s	remaining: 20m 55s
70:	learn: 0.1286077	test: 0.1285804	best: 0.1285804 (70)	total: 1m 36s	remaining: 20m 56s
71:	learn: 0.1268402	test: 0.1268139	best: 0.1268139 (71)	total: 1m 36s	remaining: 20m 46s
72:	learn: 0.1250999	test: 0.1250736	best: 0.1250736 (72)	total: 1m 37s	remaining: 20m 43s
73:	learn: 0.1234293	test: 0.1234028	best: 0.1234028 (73)	total: 1m 38s	remaining: 20m 36s
74:	learn: 0.1217972	test: 0.1217704	best: 0.1217704 (74)	total: 1m 39s	remaining: 20m 29s
75:	learn: 0.1202408	test: 0.1202144	best: 0.1202144 (75)	total: 1m 41s	remaining: 20m 31s
76:	learn: 0.1187333	test: 0.1187071	best: 0.1187071 (76)	total: 1m 42s	remaining: 20m 27s
77:	learn: 0.1172492	test: 0.1172226	best: 0.1172226 (77)	total: 1m 44s	remaining: 20m 30s
78:	learn: 0.1158249	test: 0.1157983	best: 0.1157983 (78)	total: 1m 45s	remaining: 20m 31s
79:	learn: 0.1144365	test: 0.1144091	best: 0.1144091 (79)	total: 1m 47s	remaining: 20m 34s
80:	learn: 0.1130976	test: 0.1130702	best: 0.1130702 (80)	total: 1m 49s	remaining: 20m 38s
81:	learn: 0.1117937	test: 0.1117659	best: 0.1117659 (81)	total: 1m 50s	remaining: 20m 41s
82:	learn: 0.1105420	test: 0.1105147	best: 0.1105147 (82)	total: 1m 52s	remaining: 20m 42s
83:	learn: 0.1093280	test: 0.1093005	best: 0.1093005 (83)	total: 1m 53s	remaining: 20m 36s
84:	learn: 0.1081385	test: 0.1081106	best: 0.1081106 (84)	total: 1m 55s	remaining: 20m 38s
85:	learn: 0.1069966	test: 0.1069694	best: 0.1069694 (85)	total: 1m 56s	remaining: 20m 38s
86:	learn: 0.1058809	test: 0.1058537	best: 0.1058537 (86)	total: 1m 58s	remaining: 20m 39s
87:	learn: 0.1048051	test: 0.1047776	best: 0.1047776 (87)	total: 1m 59s	remaining: 20m 33s
88:	learn: 0.1037717	test: 0.1037453	best: 0.1037453 (88)	total: 2m	remaining: 20m 36s
89:	learn: 0.1027654	test: 0.1027387	best: 0.1027387 (89)	total: 2m 1s	remaining: 20m 31s
90:	learn: 0.1017753	test: 0.1017486	best: 0.1017486 (90)	total: 2m 2s	remaining: 20m 25s
91:	learn: 0.1008260	test: 0.1008002	best: 0.1008002 (91)	total: 2m 3s	remaining: 20m 16s
92:	learn: 0.0999056	test: 0.0998799	best: 0.0998799 (92)	total: 2m 4s	remaining: 20m 12s
93:	learn: 0.0989993	test: 0.0989737	best: 0.0989737 (93)	total: 2m 6s	remaining: 20m 14s
94:	learn: 0.0981298	test: 0.0981042	best: 0.0981042 (94)	total: 2m 7s	remaining: 20m 15s
95:	learn: 0.0972874	test: 0.0972621	best: 0.0972621 (95)	total: 2m 8s	remaining: 20m 13s
96:	learn: 0.0964785	test: 0.0964540	best: 0.0964540 (96)	total: 2m 9s	remaining: 20m 5s
97:	learn: 0.0956826	test: 0.0956591	best: 0.0956591 (97)	total: 2m 10s	remaining: 20m 5s
98:	learn: 0.0949175	test: 0.0948944	best: 0.0948944 (98)	total: 2m 11s	remaining: 20m
99:	learn: 0.0941611	test: 0.0941379	best: 0.0941379 (99)	total: 2m 13s	remaining: 19m 59s
100:	learn: 0.0934393	test: 0.0934166	best: 0.0934166 (100)	total: 2m 15s	remaining: 20m 1s
101:	learn: 0.0927336	test: 0.0927111	best: 0.0927111 (101)	total: 2m 16s	remaining: 20m
102:	learn: 0.0920425	test: 0.0920198	best: 0.0920198 (102)	total: 2m 17s	remaining: 19m 54s
103:	learn: 0.0913679	test: 0.0913456	best: 0.0913456 (103)	total: 2m 18s	remaining: 19m 56s
104:	learn: 0.0907138	test: 0.0906915	best: 0.0906915 (104)	total: 2m 20s	remaining: 19m 55s
105:	learn: 0.0900819	test: 0.0900596	best: 0.0900596 (105)	total: 2m 22s	remaining: 19m 58s
106:	learn: 0.0894749	test: 0.0894530	best: 0.0894530 (106)	total: 2m 22s	remaining: 19m 51s
107:	learn: 0.0888750	test: 0.0888529	best: 0.0888529 (107)	total: 2m 24s	remaining: 19m 52s
108:	learn: 0.0882891	test: 0.0882668	best: 0.0882668 (108)	total: 2m 25s	remaining: 19m 50s
109:	learn: 0.0877237	test: 0.0877011	best: 0.0877011 (109)	total: 2m 27s	remaining: 19m 52s
110:	learn: 0.0871728	test: 0.0871501	best: 0.0871501 (110)	total: 2m 29s	remaining: 19m 54s
111:	learn: 0.0866499	test: 0.0866279	best: 0.0866279 (111)	total: 2m 29s	remaining: 19m 46s
112:	learn: 0.0861287	test: 0.0861067	best: 0.0861067 (112)	total: 2m 30s	remaining: 19m 44s
113:	learn: 0.0856202	test: 0.0855980	best: 0.0855980 (113)	total: 2m 32s	remaining: 19m 44s
114:	learn: 0.0851350	test: 0.0851130	best: 0.0851130 (114)	total: 2m 33s	remaining: 19m 43s
115:	learn: 0.0846583	test: 0.0846368	best: 0.0846368 (115)	total: 2m 34s	remaining: 19m 39s
116:	learn: 0.0842022	test: 0.0841814	best: 0.0841814 (116)	total: 2m 35s	remaining: 19m 36s
117:	learn: 0.0837500	test: 0.0837290	best: 0.0837290 (117)	total: 2m 36s	remaining: 19m 31s
118:	learn: 0.0833083	test: 0.0832872	best: 0.0832872 (118)	total: 2m 38s	remaining: 19m 31s
119:	learn: 0.0828790	test: 0.0828578	best: 0.0828578 (119)	total: 2m 40s	remaining: 19m 33s
120:	learn: 0.0824656	test: 0.0824449	best: 0.0824449 (120)	total: 2m 41s	remaining: 19m 35s
121:	learn: 0.0820651	test: 0.0820439	best: 0.0820439 (121)	total: 2m 42s	remaining: 19m 32s
122:	learn: 0.0816724	test: 0.0816511	best: 0.0816511 (122)	total: 2m 43s	remaining: 19m 28s
123:	learn: 0.0812887	test: 0.0812671	best: 0.0812671 (123)	total: 2m 45s	remaining: 19m 26s
124:	learn: 0.0809137	test: 0.0808921	best: 0.0808921 (124)	total: 2m 46s	remaining: 19m 27s
125:	learn: 0.0805549	test: 0.0805333	best: 0.0805333 (125)	total: 2m 48s	remaining: 19m 29s
126:	learn: 0.0802095	test: 0.0801883	best: 0.0801883 (126)	total: 2m 49s	remaining: 19m 23s
127:	learn: 0.0798627	test: 0.0798416	best: 0.0798416 (127)	total: 2m 50s	remaining: 19m 23s
128:	learn: 0.0795302	test: 0.0795097	best: 0.0795097 (128)	total: 2m 52s	remaining: 19m 23s
129:	learn: 0.0792064	test: 0.0791860	best: 0.0791860 (129)	total: 2m 54s	remaining: 19m 25s
130:	learn: 0.0788895	test: 0.0788695	best: 0.0788695 (130)	total: 2m 55s	remaining: 19m 22s
131:	learn: 0.0785829	test: 0.0785626	best: 0.0785626 (131)	total: 2m 57s	remaining: 19m 23s
132:	learn: 0.0782839	test: 0.0782639	best: 0.0782639 (132)	total: 2m 58s	remaining: 19m 23s
133:	learn: 0.0779921	test: 0.0779722	best: 0.0779722 (133)	total: 3m	remaining: 19m 24s
134:	learn: 0.0777085	test: 0.0776886	best: 0.0776886 (134)	total: 3m 1s	remaining: 19m 22s
135:	learn: 0.0774350	test: 0.0774157	best: 0.0774157 (135)	total: 3m 2s	remaining: 19m 17s
136:	learn: 0.0771658	test: 0.0771465	best: 0.0771465 (136)	total: 3m 3s	remaining: 19m 15s
137:	learn: 0.0769056	test: 0.0768864	best: 0.0768864 (137)	total: 3m 4s	remaining: 19m 13s
138:	learn: 0.0766533	test: 0.0766345	best: 0.0766345 (138)	total: 3m 6s	remaining: 19m 14s
139:	learn: 0.0764022	test: 0.0763833	best: 0.0763833 (139)	total: 3m 7s	remaining: 19m 13s
140:	learn: 0.0761647	test: 0.0761463	best: 0.0761463 (140)	total: 3m 8s	remaining: 19m 7s
141:	learn: 0.0759265	test: 0.0759081	best: 0.0759081 (141)	total: 3m 10s	remaining: 19m 8s
142:	learn: 0.0756938	test: 0.0756754	best: 0.0756754 (142)	total: 3m 11s	remaining: 19m 10s
143:	learn: 0.0754681	test: 0.0754494	best: 0.0754494 (143)	total: 3m 13s	remaining: 19m 8s
144:	learn: 0.0752491	test: 0.0752301	best: 0.0752301 (144)	total: 3m 14s	remaining: 19m 4s
145:	learn: 0.0750331	test: 0.0750142	best: 0.0750142 (145)	total: 3m 15s	remaining: 19m 3s
146:	learn: 0.0748290	test: 0.0748107	best: 0.0748107 (146)	total: 3m 16s	remaining: 19m
147:	learn: 0.0746257	test: 0.0746077	best: 0.0746077 (147)	total: 3m 17s	remaining: 18m 58s
148:	learn: 0.0744274	test: 0.0744092	best: 0.0744092 (148)	total: 3m 19s	remaining: 18m 57s
149:	learn: 0.0742339	test: 0.0742159	best: 0.0742159 (149)	total: 3m 20s	remaining: 18m 55s
150:	learn: 0.0740447	test: 0.0740265	best: 0.0740265 (150)	total: 3m 21s	remaining: 18m 52s
151:	learn: 0.0738640	test: 0.0738465	best: 0.0738465 (151)	total: 3m 22s	remaining: 18m 49s
152:	learn: 0.0736891	test: 0.0736719	best: 0.0736719 (152)	total: 3m 23s	remaining: 18m 46s
153:	learn: 0.0735178	test: 0.0735007	best: 0.0735007 (153)	total: 3m 25s	remaining: 18m 46s
154:	learn: 0.0733430	test: 0.0733258	best: 0.0733258 (154)	total: 3m 26s	remaining: 18m 47s
155:	learn: 0.0731767	test: 0.0731595	best: 0.0731595 (155)	total: 3m 28s	remaining: 18m 46s
156:	learn: 0.0730140	test: 0.0729968	best: 0.0729968 (156)	total: 3m 29s	remaining: 18m 44s
157:	learn: 0.0728533	test: 0.0728361	best: 0.0728361 (157)	total: 3m 30s	remaining: 18m 43s
158:	learn: 0.0726981	test: 0.0726808	best: 0.0726808 (158)	total: 3m 32s	remaining: 18m 44s
159:	learn: 0.0725507	test: 0.0725337	best: 0.0725337 (159)	total: 3m 33s	remaining: 18m 42s
160:	learn: 0.0724032	test: 0.0723861	best: 0.0723861 (160)	total: 3m 34s	remaining: 18m 40s
161:	learn: 0.0722607	test: 0.0722435	best: 0.0722435 (161)	total: 3m 35s	remaining: 18m 35s
162:	learn: 0.0721235	test: 0.0721067	best: 0.0721067 (162)	total: 3m 36s	remaining: 18m 32s
163:	learn: 0.0719889	test: 0.0719727	best: 0.0719727 (163)	total: 3m 37s	remaining: 18m 28s
164:	learn: 0.0718566	test: 0.0718401	best: 0.0718401 (164)	total: 3m 39s	remaining: 18m 28s
165:	learn: 0.0717262	test: 0.0717095	best: 0.0717095 (165)	total: 3m 40s	remaining: 18m 29s
166:	learn: 0.0716035	test: 0.0715873	best: 0.0715873 (166)	total: 3m 41s	remaining: 18m 25s
167:	learn: 0.0714788	test: 0.0714621	best: 0.0714621 (167)	total: 3m 43s	remaining: 18m 26s
168:	learn: 0.0713578	test: 0.0713410	best: 0.0713410 (168)	total: 3m 44s	remaining: 18m 24s
169:	learn: 0.0712420	test: 0.0712255	best: 0.0712255 (169)	total: 3m 45s	remaining: 18m 21s
170:	learn: 0.0711262	test: 0.0711098	best: 0.0711098 (170)	total: 3m 47s	remaining: 18m 20s
171:	learn: 0.0710148	test: 0.0709984	best: 0.0709984 (171)	total: 3m 48s	remaining: 18m 21s
172:	learn: 0.0709048	test: 0.0708879	best: 0.0708879 (172)	total: 3m 50s	remaining: 18m 21s
173:	learn: 0.0707979	test: 0.0707806	best: 0.0707806 (173)	total: 3m 51s	remaining: 18m 17s
174:	learn: 0.0706949	test: 0.0706775	best: 0.0706775 (174)	total: 3m 51s	remaining: 18m 13s
175:	learn: 0.0705918	test: 0.0705744	best: 0.0705744 (175)	total: 3m 53s	remaining: 18m 12s
176:	learn: 0.0704899	test: 0.0704724	best: 0.0704724 (176)	total: 3m 55s	remaining: 18m 12s
177:	learn: 0.0703934	test: 0.0703761	best: 0.0703761 (177)	total: 3m 56s	remaining: 18m 11s
178:	learn: 0.0703012	test: 0.0702844	best: 0.0702844 (178)	total: 3m 57s	remaining: 18m 9s
179:	learn: 0.0702066	test: 0.0701895	best: 0.0701895 (179)	total: 3m 59s	remaining: 18m 9s
180:	learn: 0.0701186	test: 0.0701019	best: 0.0701019 (180)	total: 3m 59s	remaining: 18m 5s
181:	learn: 0.0700315	test: 0.0700148	best: 0.0700148 (181)	total: 4m	remaining: 18m 2s
182:	learn: 0.0699475	test: 0.0699308	best: 0.0699308 (182)	total: 4m 1s	remaining: 18m
183:	learn: 0.0698633	test: 0.0698467	best: 0.0698467 (183)	total: 4m 3s	remaining: 18m
184:	learn: 0.0697837	test: 0.0697675	best: 0.0697675 (184)	total: 4m 4s	remaining: 17m 57s
185:	learn: 0.0697038	test: 0.0696878	best: 0.0696878 (185)	total: 4m 5s	remaining: 17m 55s
186:	learn: 0.0696222	test: 0.0696060	best: 0.0696060 (186)	total: 4m 7s	remaining: 17m 55s
187:	learn: 0.0695445	test: 0.0695285	best: 0.0695285 (187)	total: 4m 8s	remaining: 17m 53s
188:	learn: 0.0694721	test: 0.0694560	best: 0.0694560 (188)	total: 4m 9s	remaining: 17m 51s
189:	learn: 0.0694006	test: 0.0693847	best: 0.0693847 (189)	total: 4m 10s	remaining: 17m 49s
190:	learn: 0.0693305	test: 0.0693145	best: 0.0693145 (190)	total: 4m 11s	remaining: 17m 46s
191:	learn: 0.0692609	test: 0.0692446	best: 0.0692446 (191)	total: 4m 12s	remaining: 17m 42s
192:	learn: 0.0691924	test: 0.0691761	best: 0.0691761 (192)	total: 4m 14s	remaining: 17m 42s
193:	learn: 0.0691262	test: 0.0691102	best: 0.0691102 (193)	total: 4m 15s	remaining: 17m 40s
194:	learn: 0.0690628	test: 0.0690469	best: 0.0690469 (194)	total: 4m 16s	remaining: 17m 40s
195:	learn: 0.0690014	test: 0.0689855	best: 0.0689855 (195)	total: 4m 18s	remaining: 17m 38s
196:	learn: 0.0689396	test: 0.0689239	best: 0.0689239 (196)	total: 4m 19s	remaining: 17m 37s
197:	learn: 0.0688781	test: 0.0688622	best: 0.0688622 (197)	total: 4m 20s	remaining: 17m 36s
198:	learn: 0.0688207	test: 0.0688049	best: 0.0688049 (198)	total: 4m 21s	remaining: 17m 33s
199:	learn: 0.0687631	test: 0.0687474	best: 0.0687474 (199)	total: 4m 23s	remaining: 17m 32s
200:	learn: 0.0687062	test: 0.0686907	best: 0.0686907 (200)	total: 4m 24s	remaining: 17m 31s
201:	learn: 0.0686496	test: 0.0686342	best: 0.0686342 (201)	total: 4m 26s	remaining: 17m 31s
202:	learn: 0.0685958	test: 0.0685807	best: 0.0685807 (202)	total: 4m 28s	remaining: 17m 32s
203:	learn: 0.0685450	test: 0.0685303	best: 0.0685303 (203)	total: 4m 29s	remaining: 17m 30s
204:	learn: 0.0684938	test: 0.0684787	best: 0.0684787 (204)	total: 4m 30s	remaining: 17m 27s
205:	learn: 0.0684437	test: 0.0684287	best: 0.0684287 (205)	total: 4m 30s	remaining: 17m 23s
206:	learn: 0.0683926	test: 0.0683776	best: 0.0683776 (206)	total: 4m 32s	remaining: 17m 22s
207:	learn: 0.0683446	test: 0.0683296	best: 0.0683296 (207)	total: 4m 33s	remaining: 17m 21s
208:	learn: 0.0682965	test: 0.0682813	best: 0.0682813 (208)	total: 4m 34s	remaining: 17m 19s
209:	learn: 0.0682499	test: 0.0682342	best: 0.0682342 (209)	total: 4m 36s	remaining: 17m 19s
210:	learn: 0.0682043	test: 0.0681887	best: 0.0681887 (210)	total: 4m 37s	remaining: 17m 19s
211:	learn: 0.0681600	test: 0.0681445	best: 0.0681445 (211)	total: 4m 39s	remaining: 17m 18s
212:	learn: 0.0681169	test: 0.0681010	best: 0.0681010 (212)	total: 4m 40s	remaining: 17m 15s
213:	learn: 0.0680748	test: 0.0680587	best: 0.0680587 (213)	total: 4m 41s	remaining: 17m 13s
214:	learn: 0.0680340	test: 0.0680177	best: 0.0680177 (214)	total: 4m 43s	remaining: 17m 13s
215:	learn: 0.0679949	test: 0.0679792	best: 0.0679792 (215)	total: 4m 44s	remaining: 17m 13s
216:	learn: 0.0679547	test: 0.0679390	best: 0.0679390 (216)	total: 4m 46s	remaining: 17m 12s
217:	learn: 0.0679171	test: 0.0679016	best: 0.0679016 (217)	total: 4m 47s	remaining: 17m 9s
218:	learn: 0.0678794	test: 0.0678639	best: 0.0678639 (218)	total: 4m 48s	remaining: 17m 10s
219:	learn: 0.0678402	test: 0.0678247	best: 0.0678247 (219)	total: 4m 50s	remaining: 17m 10s
220:	learn: 0.0678036	test: 0.0677882	best: 0.0677882 (220)	total: 4m 52s	remaining: 17m 9s
221:	learn: 0.0677698	test: 0.0677545	best: 0.0677545 (221)	total: 4m 53s	remaining: 17m 7s
222:	learn: 0.0677341	test: 0.0677185	best: 0.0677185 (222)	total: 4m 54s	remaining: 17m 7s
223:	learn: 0.0677006	test: 0.0676853	best: 0.0676853 (223)	total: 4m 56s	remaining: 17m 5s
224:	learn: 0.0676674	test: 0.0676523	best: 0.0676523 (224)	total: 4m 57s	remaining: 17m 5s
225:	learn: 0.0676351	test: 0.0676196	best: 0.0676196 (225)	total: 4m 59s	remaining: 17m 4s
226:	learn: 0.0676036	test: 0.0675880	best: 0.0675880 (226)	total: 5m	remaining: 17m 3s
227:	learn: 0.0675723	test: 0.0675565	best: 0.0675565 (227)	total: 5m 1s	remaining: 17m 2s
228:	learn: 0.0675435	test: 0.0675281	best: 0.0675281 (228)	total: 5m 3s	remaining: 17m
229:	learn: 0.0675136	test: 0.0674980	best: 0.0674980 (229)	total: 5m 4s	remaining: 16m 59s
230:	learn: 0.0674839	test: 0.0674682	best: 0.0674682 (230)	total: 5m 6s	remaining: 16m 59s
231:	learn: 0.0674559	test: 0.0674403	best: 0.0674403 (231)	total: 5m 7s	remaining: 16m 58s
232:	learn: 0.0674274	test: 0.0674115	best: 0.0674115 (232)	total: 5m 9s	remaining: 16m 58s
233:	learn: 0.0674001	test: 0.0673844	best: 0.0673844 (233)	total: 5m 11s	remaining: 16m 58s
234:	learn: 0.0673745	test: 0.0673589	best: 0.0673589 (234)	total: 5m 12s	remaining: 16m 56s
235:	learn: 0.0673499	test: 0.0673345	best: 0.0673345 (235)	total: 5m 12s	remaining: 16m 52s
236:	learn: 0.0673243	test: 0.0673090	best: 0.0673090 (236)	total: 5m 14s	remaining: 16m 53s
237:	learn: 0.0672998	test: 0.0672845	best: 0.0672845 (237)	total: 5m 15s	remaining: 16m 50s
238:	learn: 0.0672740	test: 0.0672589	best: 0.0672589 (238)	total: 5m 17s	remaining: 16m 50s
239:	learn: 0.0672492	test: 0.0672339	best: 0.0672339 (239)	total: 5m 19s	remaining: 16m 50s
240:	learn: 0.0672252	test: 0.0672099	best: 0.0672099 (240)	total: 5m 20s	remaining: 16m 49s
241:	learn: 0.0672011	test: 0.0671855	best: 0.0671855 (241)	total: 5m 22s	remaining: 16m 48s
242:	learn: 0.0671777	test: 0.0671625	best: 0.0671625 (242)	total: 5m 23s	remaining: 16m 48s
243:	learn: 0.0671567	test: 0.0671415	best: 0.0671415 (243)	total: 5m 24s	remaining: 16m 46s
244:	learn: 0.0671352	test: 0.0671200	best: 0.0671200 (244)	total: 5m 26s	remaining: 16m 45s
245:	learn: 0.0671137	test: 0.0670981	best: 0.0670981 (245)	total: 5m 27s	remaining: 16m 45s
246:	learn: 0.0670934	test: 0.0670779	best: 0.0670779 (246)	total: 5m 28s	remaining: 16m 42s
247:	learn: 0.0670727	test: 0.0670569	best: 0.0670569 (247)	total: 5m 30s	remaining: 16m 40s
248:	learn: 0.0670519	test: 0.0670360	best: 0.0670360 (248)	total: 5m 31s	remaining: 16m 40s
249:	learn: 0.0670327	test: 0.0670166	best: 0.0670166 (249)	total: 5m 32s	remaining: 16m 38s
250:	learn: 0.0670142	test: 0.0669980	best: 0.0669980 (250)	total: 5m 34s	remaining: 16m 37s
251:	learn: 0.0669952	test: 0.0669793	best: 0.0669793 (251)	total: 5m 35s	remaining: 16m 35s
252:	learn: 0.0669771	test: 0.0669611	best: 0.0669611 (252)	total: 5m 36s	remaining: 16m 33s
253:	learn: 0.0669593	test: 0.0669430	best: 0.0669430 (253)	total: 5m 38s	remaining: 16m 33s
254:	learn: 0.0669420	test: 0.0669256	best: 0.0669256 (254)	total: 5m 39s	remaining: 16m 30s
255:	learn: 0.0669255	test: 0.0669092	best: 0.0669092 (255)	total: 5m 39s	remaining: 16m 28s
256:	learn: 0.0669097	test: 0.0668933	best: 0.0668933 (256)	total: 5m 40s	remaining: 16m 24s
257:	learn: 0.0668928	test: 0.0668764	best: 0.0668764 (257)	total: 5m 42s	remaining: 16m 24s
258:	learn: 0.0668782	test: 0.0668619	best: 0.0668619 (258)	total: 5m 43s	remaining: 16m 21s
259:	learn: 0.0668623	test: 0.0668461	best: 0.0668461 (259)	total: 5m 44s	remaining: 16m 21s
260:	learn: 0.0668470	test: 0.0668308	best: 0.0668308 (260)	total: 5m 46s	remaining: 16m 20s
261:	learn: 0.0668332	test: 0.0668171	best: 0.0668171 (261)	total: 5m 47s	remaining: 16m 18s
262:	learn: 0.0668177	test: 0.0668014	best: 0.0668014 (262)	total: 5m 49s	remaining: 16m 18s
263:	learn: 0.0668039	test: 0.0667876	best: 0.0667876 (263)	total: 5m 50s	remaining: 16m 16s
264:	learn: 0.0667888	test: 0.0667724	best: 0.0667724 (264)	total: 5m 51s	remaining: 16m 16s
265:	learn: 0.0667752	test: 0.0667589	best: 0.0667589 (265)	total: 5m 52s	remaining: 16m 13s
266:	learn: 0.0667614	test: 0.0667451	best: 0.0667451 (266)	total: 5m 54s	remaining: 16m 12s
267:	learn: 0.0667481	test: 0.0667319	best: 0.0667319 (267)	total: 5m 55s	remaining: 16m 12s
268:	learn: 0.0667349	test: 0.0667186	best: 0.0667186 (268)	total: 5m 57s	remaining: 16m 10s
269:	learn: 0.0667224	test: 0.0667061	best: 0.0667061 (269)	total: 5m 58s	remaining: 16m 10s
270:	learn: 0.0667102	test: 0.0666937	best: 0.0666937 (270)	total: 5m 59s	remaining: 16m 7s
271:	learn: 0.0666982	test: 0.0666820	best: 0.0666820 (271)	total: 6m 1s	remaining: 16m 6s
272:	learn: 0.0666859	test: 0.0666700	best: 0.0666700 (272)	total: 6m 2s	remaining: 16m 6s
273:	learn: 0.0666755	test: 0.0666596	best: 0.0666596 (273)	total: 6m 3s	remaining: 16m 2s
274:	learn: 0.0666637	test: 0.0666478	best: 0.0666478 (274)	total: 6m 5s	remaining: 16m 2s
275:	learn: 0.0666518	test: 0.0666361	best: 0.0666361 (275)	total: 6m 6s	remaining: 16m 1s
276:	learn: 0.0666417	test: 0.0666261	best: 0.0666261 (276)	total: 6m 7s	remaining: 16m
277:	learn: 0.0666312	test: 0.0666155	best: 0.0666155 (277)	total: 6m 8s	remaining: 15m 57s
278:	learn: 0.0666204	test: 0.0666049	best: 0.0666049 (278)	total: 6m 10s	remaining: 15m 57s
279:	learn: 0.0666101	test: 0.0665946	best: 0.0665946 (279)	total: 6m 12s	remaining: 15m 57s
280:	learn: 0.0665998	test: 0.0665840	best: 0.0665840 (280)	total: 6m 13s	remaining: 15m 56s
281:	learn: 0.0665903	test: 0.0665746	best: 0.0665746 (281)	total: 6m 14s	remaining: 15m 53s
282:	learn: 0.0665806	test: 0.0665649	best: 0.0665649 (282)	total: 6m 15s	remaining: 15m 52s
283:	learn: 0.0665716	test: 0.0665559	best: 0.0665559 (283)	total: 6m 16s	remaining: 15m 49s
284:	learn: 0.0665627	test: 0.0665470	best: 0.0665470 (284)	total: 6m 17s	remaining: 15m 48s
285:	learn: 0.0665540	test: 0.0665386	best: 0.0665386 (285)	total: 6m 18s	remaining: 15m 46s
286:	learn: 0.0665450	test: 0.0665294	best: 0.0665294 (286)	total: 6m 20s	remaining: 15m 45s
287:	learn: 0.0665357	test: 0.0665203	best: 0.0665203 (287)	total: 6m 22s	remaining: 15m 44s
288:	learn: 0.0665270	test: 0.0665119	best: 0.0665119 (288)	total: 6m 23s	remaining: 15m 44s
289:	learn: 0.0665183	test: 0.0665032	best: 0.0665032 (289)	total: 6m 25s	remaining: 15m 43s
290:	learn: 0.0665106	test: 0.0664955	best: 0.0664955 (290)	total: 6m 26s	remaining: 15m 41s
291:	learn: 0.0665024	test: 0.0664873	best: 0.0664873 (291)	total: 6m 27s	remaining: 15m 40s
292:	learn: 0.0664938	test: 0.0664788	best: 0.0664788 (292)	total: 6m 29s	remaining: 15m 39s
293:	learn: 0.0664861	test: 0.0664713	best: 0.0664713 (293)	total: 6m 30s	remaining: 15m 38s
294:	learn: 0.0664791	test: 0.0664646	best: 0.0664646 (294)	total: 6m 31s	remaining: 15m 35s
295:	learn: 0.0664720	test: 0.0664575	best: 0.0664575 (295)	total: 6m 32s	remaining: 15m 34s
296:	learn: 0.0664649	test: 0.0664507	best: 0.0664507 (296)	total: 6m 33s	remaining: 15m 32s
297:	learn: 0.0664580	test: 0.0664438	best: 0.0664438 (297)	total: 6m 34s	remaining: 15m 30s
298:	learn: 0.0664514	test: 0.0664370	best: 0.0664370 (298)	total: 6m 35s	remaining: 15m 27s
299:	learn: 0.0664448	test: 0.0664306	best: 0.0664306 (299)	total: 6m 37s	remaining: 15m 26s
300:	learn: 0.0664380	test: 0.0664239	best: 0.0664239 (300)	total: 6m 38s	remaining: 15m 25s
301:	learn: 0.0664322	test: 0.0664183	best: 0.0664183 (301)	total: 6m 38s	remaining: 15m 21s
302:	learn: 0.0664252	test: 0.0664112	best: 0.0664112 (302)	total: 6m 40s	remaining: 15m 20s
303:	learn: 0.0664185	test: 0.0664046	best: 0.0664046 (303)	total: 6m 41s	remaining: 15m 19s
304:	learn: 0.0664115	test: 0.0663976	best: 0.0663976 (304)	total: 6m 43s	remaining: 15m 19s
305:	learn: 0.0664050	test: 0.0663911	best: 0.0663911 (305)	total: 6m 44s	remaining: 15m 18s
306:	learn: 0.0663992	test: 0.0663850	best: 0.0663850 (306)	total: 6m 45s	remaining: 15m 15s
307:	learn: 0.0663930	test: 0.0663787	best: 0.0663787 (307)	total: 6m 46s	remaining: 15m 13s
308:	learn: 0.0663877	test: 0.0663735	best: 0.0663735 (308)	total: 6m 47s	remaining: 15m 11s
309:	learn: 0.0663823	test: 0.0663680	best: 0.0663680 (309)	total: 6m 49s	remaining: 15m 10s
310:	learn: 0.0663767	test: 0.0663621	best: 0.0663621 (310)	total: 6m 50s	remaining: 15m 10s
311:	learn: 0.0663715	test: 0.0663568	best: 0.0663568 (311)	total: 6m 52s	remaining: 15m 8s
312:	learn: 0.0663658	test: 0.0663509	best: 0.0663509 (312)	total: 6m 53s	remaining: 15m 7s
313:	learn: 0.0663608	test: 0.0663459	best: 0.0663459 (313)	total: 6m 54s	remaining: 15m 4s
314:	learn: 0.0663562	test: 0.0663413	best: 0.0663413 (314)	total: 6m 54s	remaining: 15m 1s
315:	learn: 0.0663500	test: 0.0663352	best: 0.0663352 (315)	total: 6m 56s	remaining: 15m 1s
316:	learn: 0.0663452	test: 0.0663305	best: 0.0663305 (316)	total: 6m 57s	remaining: 14m 59s
317:	learn: 0.0663398	test: 0.0663251	best: 0.0663251 (317)	total: 6m 59s	remaining: 14m 58s
318:	learn: 0.0663342	test: 0.0663196	best: 0.0663196 (318)	total: 7m	remaining: 14m 57s
319:	learn: 0.0663292	test: 0.0663147	best: 0.0663147 (319)	total: 7m 2s	remaining: 14m 56s
320:	learn: 0.0663245	test: 0.0663101	best: 0.0663101 (320)	total: 7m 3s	remaining: 14m 55s
321:	learn: 0.0663201	test: 0.0663057	best: 0.0663057 (321)	total: 7m 5s	remaining: 14m 54s
322:	learn: 0.0663163	test: 0.0663020	best: 0.0663020 (322)	total: 7m 5s	remaining: 14m 52s
323:	learn: 0.0663127	test: 0.0662984	best: 0.0662984 (323)	total: 7m 6s	remaining: 14m 50s
324:	learn: 0.0663087	test: 0.0662944	best: 0.0662944 (324)	total: 7m 8s	remaining: 14m 49s
325:	learn: 0.0663045	test: 0.0662903	best: 0.0662903 (325)	total: 7m 9s	remaining: 14m 48s
326:	learn: 0.0663008	test: 0.0662866	best: 0.0662866 (326)	total: 7m 11s	remaining: 14m 47s
327:	learn: 0.0662965	test: 0.0662822	best: 0.0662822 (327)	total: 7m 12s	remaining: 14m 45s
328:	learn: 0.0662926	test: 0.0662785	best: 0.0662785 (328)	total: 7m 13s	remaining: 14m 45s
329:	learn: 0.0662890	test: 0.0662750	best: 0.0662750 (329)	total: 7m 15s	remaining: 14m 43s
330:	learn: 0.0662852	test: 0.0662715	best: 0.0662715 (330)	total: 7m 16s	remaining: 14m 42s
331:	learn: 0.0662807	test: 0.0662671	best: 0.0662671 (331)	total: 7m 18s	remaining: 14m 42s
332:	learn: 0.0662770	test: 0.0662634	best: 0.0662634 (332)	total: 7m 19s	remaining: 14m 40s
333:	learn: 0.0662734	test: 0.0662598	best: 0.0662598 (333)	total: 7m 20s	remaining: 14m 39s
334:	learn: 0.0662697	test: 0.0662563	best: 0.0662563 (334)	total: 7m 22s	remaining: 14m 38s
335:	learn: 0.0662659	test: 0.0662526	best: 0.0662526 (335)	total: 7m 23s	remaining: 14m 36s
336:	learn: 0.0662621	test: 0.0662487	best: 0.0662487 (336)	total: 7m 25s	remaining: 14m 36s
337:	learn: 0.0662588	test: 0.0662453	best: 0.0662453 (337)	total: 7m 26s	remaining: 14m 34s
338:	learn: 0.0662556	test: 0.0662424	best: 0.0662424 (338)	total: 7m 27s	remaining: 14m 33s
339:	learn: 0.0662521	test: 0.0662390	best: 0.0662390 (339)	total: 7m 29s	remaining: 14m 32s
340:	learn: 0.0662491	test: 0.0662361	best: 0.0662361 (340)	total: 7m 30s	remaining: 14m 30s
341:	learn: 0.0662460	test: 0.0662330	best: 0.0662330 (341)	total: 7m 31s	remaining: 14m 28s
342:	learn: 0.0662426	test: 0.0662296	best: 0.0662296 (342)	total: 7m 32s	remaining: 14m 27s
343:	learn: 0.0662399	test: 0.0662268	best: 0.0662268 (343)	total: 7m 34s	remaining: 14m 26s
344:	learn: 0.0662368	test: 0.0662236	best: 0.0662236 (344)	total: 7m 35s	remaining: 14m 25s
345:	learn: 0.0662335	test: 0.0662204	best: 0.0662204 (345)	total: 7m 37s	remaining: 14m 25s
346:	learn: 0.0662309	test: 0.0662177	best: 0.0662177 (346)	total: 7m 38s	remaining: 14m 23s
347:	learn: 0.0662282	test: 0.0662150	best: 0.0662150 (347)	total: 7m 40s	remaining: 14m 22s
348:	learn: 0.0662254	test: 0.0662122	best: 0.0662122 (348)	total: 7m 41s	remaining: 14m 20s
349:	learn: 0.0662223	test: 0.0662092	best: 0.0662092 (349)	total: 7m 43s	remaining: 14m 20s
350:	learn: 0.0662196	test: 0.0662063	best: 0.0662063 (350)	total: 7m 44s	remaining: 14m 18s
351:	learn: 0.0662167	test: 0.0662034	best: 0.0662034 (351)	total: 7m 45s	remaining: 14m 17s
352:	learn: 0.0662142	test: 0.0662007	best: 0.0662007 (352)	total: 7m 46s	remaining: 14m 15s
353:	learn: 0.0662118	test: 0.0661983	best: 0.0661983 (353)	total: 7m 47s	remaining: 14m 13s
354:	learn: 0.0662092	test: 0.0661958	best: 0.0661958 (354)	total: 7m 49s	remaining: 14m 12s
355:	learn: 0.0662069	test: 0.0661937	best: 0.0661937 (355)	total: 7m 50s	remaining: 14m 11s
356:	learn: 0.0662049	test: 0.0661919	best: 0.0661919 (356)	total: 7m 51s	remaining: 14m 9s
357:	learn: 0.0662022	test: 0.0661893	best: 0.0661893 (357)	total: 7m 53s	remaining: 14m 9s
358:	learn: 0.0662002	test: 0.0661872	best: 0.0661872 (358)	total: 7m 54s	remaining: 14m 7s
359:	learn: 0.0661978	test: 0.0661850	best: 0.0661850 (359)	total: 7m 56s	remaining: 14m 6s
360:	learn: 0.0661950	test: 0.0661823	best: 0.0661823 (360)	total: 7m 57s	remaining: 14m 5s
361:	learn: 0.0661934	test: 0.0661808	best: 0.0661808 (361)	total: 7m 58s	remaining: 14m 2s
362:	learn: 0.0661916	test: 0.0661791	best: 0.0661791 (362)	total: 7m 59s	remaining: 14m 1s
363:	learn: 0.0661894	test: 0.0661769	best: 0.0661769 (363)	total: 8m	remaining: 14m
364:	learn: 0.0661875	test: 0.0661749	best: 0.0661749 (364)	total: 8m 1s	remaining: 13m 57s
365:	learn: 0.0661851	test: 0.0661724	best: 0.0661724 (365)	total: 8m 2s	remaining: 13m 56s
366:	learn: 0.0661829	test: 0.0661704	best: 0.0661704 (366)	total: 8m 4s	remaining: 13m 55s
367:	learn: 0.0661810	test: 0.0661684	best: 0.0661684 (367)	total: 8m 5s	remaining: 13m 54s
368:	learn: 0.0661791	test: 0.0661666	best: 0.0661666 (368)	total: 8m 7s	remaining: 13m 52s
369:	learn: 0.0661775	test: 0.0661650	best: 0.0661650 (369)	total: 8m 7s	remaining: 13m 50s
370:	learn: 0.0661754	test: 0.0661629	best: 0.0661629 (370)	total: 8m 9s	remaining: 13m 50s
371:	learn: 0.0661735	test: 0.0661610	best: 0.0661610 (371)	total: 8m 11s	remaining: 13m 49s
372:	learn: 0.0661721	test: 0.0661597	best: 0.0661597 (372)	total: 8m 11s	remaining: 13m 46s
373:	learn: 0.0661703	test: 0.0661579	best: 0.0661579 (373)	total: 8m 13s	remaining: 13m 45s
374:	learn: 0.0661686	test: 0.0661561	best: 0.0661561 (374)	total: 8m 14s	remaining: 13m 43s
375:	learn: 0.0661669	test: 0.0661544	best: 0.0661544 (375)	total: 8m 15s	remaining: 13m 42s
376:	learn: 0.0661652	test: 0.0661527	best: 0.0661527 (376)	total: 8m 17s	remaining: 13m 41s
377:	learn: 0.0661636	test: 0.0661511	best: 0.0661511 (377)	total: 8m 18s	remaining: 13m 39s
378:	learn: 0.0661619	test: 0.0661494	best: 0.0661494 (378)	total: 8m 19s	remaining: 13m 38s
379:	learn: 0.0661601	test: 0.0661475	best: 0.0661475 (379)	total: 8m 20s	remaining: 13m 37s
380:	learn: 0.0661582	test: 0.0661458	best: 0.0661458 (380)	total: 8m 22s	remaining: 13m 36s
381:	learn: 0.0661562	test: 0.0661438	best: 0.0661438 (381)	total: 8m 24s	remaining: 13m 35s
382:	learn: 0.0661549	test: 0.0661426	best: 0.0661426 (382)	total: 8m 25s	remaining: 13m 34s
383:	learn: 0.0661535	test: 0.0661412	best: 0.0661412 (383)	total: 8m 26s	remaining: 13m 33s
384:	learn: 0.0661523	test: 0.0661399	best: 0.0661399 (384)	total: 8m 27s	remaining: 13m 31s
385:	learn: 0.0661508	test: 0.0661383	best: 0.0661383 (385)	total: 8m 29s	remaining: 13m 29s
386:	learn: 0.0661494	test: 0.0661370	best: 0.0661370 (386)	total: 8m 30s	remaining: 13m 28s
387:	learn: 0.0661480	test: 0.0661357	best: 0.0661357 (387)	total: 8m 31s	remaining: 13m 26s
388:	learn: 0.0661465	test: 0.0661341	best: 0.0661341 (388)	total: 8m 32s	remaining: 13m 25s
389:	learn: 0.0661454	test: 0.0661329	best: 0.0661329 (389)	total: 8m 33s	remaining: 13m 23s
390:	learn: 0.0661442	test: 0.0661319	best: 0.0661319 (390)	total: 8m 35s	remaining: 13m 22s
391:	learn: 0.0661425	test: 0.0661309	best: 0.0661309 (391)	total: 8m 36s	remaining: 13m 21s
392:	learn: 0.0661413	test: 0.0661297	best: 0.0661297 (392)	total: 8m 38s	remaining: 13m 20s
393:	learn: 0.0661398	test: 0.0661280	best: 0.0661280 (393)	total: 8m 40s	remaining: 13m 19s
394:	learn: 0.0661386	test: 0.0661269	best: 0.0661269 (394)	total: 8m 41s	remaining: 13m 18s
395:	learn: 0.0661374	test: 0.0661256	best: 0.0661256 (395)	total: 8m 42s	remaining: 13m 16s
396:	learn: 0.0661363	test: 0.0661246	best: 0.0661246 (396)	total: 8m 43s	remaining: 13m 14s
397:	learn: 0.0661351	test: 0.0661235	best: 0.0661235 (397)	total: 8m 45s	remaining: 13m 14s
398:	learn: 0.0661339	test: 0.0661222	best: 0.0661222 (398)	total: 8m 46s	remaining: 13m 12s
399:	learn: 0.0661326	test: 0.0661210	best: 0.0661210 (399)	total: 8m 48s	remaining: 13m 12s
400:	learn: 0.0661316	test: 0.0661201	best: 0.0661201 (400)	total: 8m 49s	remaining: 13m 10s
401:	learn: 0.0661305	test: 0.0661189	best: 0.0661189 (401)	total: 8m 50s	remaining: 13m 8s
402:	learn: 0.0661294	test: 0.0661179	best: 0.0661179 (402)	total: 8m 51s	remaining: 13m 7s
403:	learn: 0.0661282	test: 0.0661167	best: 0.0661167 (403)	total: 8m 53s	remaining: 13m 6s
404:	learn: 0.0661273	test: 0.0661159	best: 0.0661159 (404)	total: 8m 54s	remaining: 13m 4s
405:	learn: 0.0661265	test: 0.0661152	best: 0.0661152 (405)	total: 8m 55s	remaining: 13m 3s
406:	learn: 0.0661253	test: 0.0661143	best: 0.0661143 (406)	total: 8m 56s	remaining: 13m 2s
407:	learn: 0.0661244	test: 0.0661133	best: 0.0661133 (407)	total: 8m 58s	remaining: 13m
408:	learn: 0.0661235	test: 0.0661126	best: 0.0661126 (408)	total: 8m 59s	remaining: 12m 59s
409:	learn: 0.0661225	test: 0.0661117	best: 0.0661117 (409)	total: 9m 1s	remaining: 12m 59s
410:	learn: 0.0661215	test: 0.0661107	best: 0.0661107 (410)	total: 9m 2s	remaining: 12m 57s
411:	learn: 0.0661205	test: 0.0661096	best: 0.0661096 (411)	total: 9m 3s	remaining: 12m 55s
412:	learn: 0.0661196	test: 0.0661088	best: 0.0661088 (412)	total: 9m 4s	remaining: 12m 54s
413:	learn: 0.0661187	test: 0.0661079	best: 0.0661079 (413)	total: 9m 6s	remaining: 12m 53s
414:	learn: 0.0661180	test: 0.0661072	best: 0.0661072 (414)	total: 9m 7s	remaining: 12m 51s
415:	learn: 0.0661171	test: 0.0661063	best: 0.0661063 (415)	total: 9m 8s	remaining: 12m 50s
416:	learn: 0.0661164	test: 0.0661056	best: 0.0661056 (416)	total: 9m 10s	remaining: 12m 49s
417:	learn: 0.0661157	test: 0.0661048	best: 0.0661048 (417)	total: 9m 10s	remaining: 12m 47s
418:	learn: 0.0661151	test: 0.0661042	best: 0.0661042 (418)	total: 9m 11s	remaining: 12m 44s
419:	learn: 0.0661142	test: 0.0661033	best: 0.0661033 (419)	total: 9m 12s	remaining: 12m 43s
420:	learn: 0.0661137	test: 0.0661028	best: 0.0661028 (420)	total: 9m 13s	remaining: 12m 40s
421:	learn: 0.0661127	test: 0.0661017	best: 0.0661017 (421)	total: 9m 14s	remaining: 12m 40s
422:	learn: 0.0661118	test: 0.0661009	best: 0.0661009 (422)	total: 9m 16s	remaining: 12m 39s
423:	learn: 0.0661109	test: 0.0660999	best: 0.0660999 (423)	total: 9m 18s	remaining: 12m 38s
424:	learn: 0.0661099	test: 0.0660991	best: 0.0660991 (424)	total: 9m 20s	remaining: 12m 37s
425:	learn: 0.0661094	test: 0.0660986	best: 0.0660986 (425)	total: 9m 20s	remaining: 12m 35s
426:	learn: 0.0661087	test: 0.0660977	best: 0.0660977 (426)	total: 9m 21s	remaining: 12m 34s
427:	learn: 0.0661079	test: 0.0660970	best: 0.0660970 (427)	total: 9m 23s	remaining: 12m 32s
428:	learn: 0.0661068	test: 0.0660960	best: 0.0660960 (428)	total: 9m 25s	remaining: 12m 32s
429:	learn: 0.0661059	test: 0.0660953	best: 0.0660953 (429)	total: 9m 26s	remaining: 12m 31s
430:	learn: 0.0661049	test: 0.0660945	best: 0.0660945 (430)	total: 9m 28s	remaining: 12m 30s
431:	learn: 0.0661042	test: 0.0660938	best: 0.0660938 (431)	total: 9m 29s	remaining: 12m 28s
432:	learn: 0.0661038	test: 0.0660934	best: 0.0660934 (432)	total: 9m 30s	remaining: 12m 26s
433:	learn: 0.0661029	test: 0.0660925	best: 0.0660925 (433)	total: 9m 31s	remaining: 12m 25s
434:	learn: 0.0661022	test: 0.0660918	best: 0.0660918 (434)	total: 9m 33s	remaining: 12m 24s
435:	learn: 0.0661017	test: 0.0660914	best: 0.0660914 (435)	total: 9m 33s	remaining: 12m 22s
436:	learn: 0.0661010	test: 0.0660906	best: 0.0660906 (436)	total: 9m 35s	remaining: 12m 20s
437:	learn: 0.0661004	test: 0.0660901	best: 0.0660901 (437)	total: 9m 36s	remaining: 12m 19s
438:	learn: 0.0660995	test: 0.0660892	best: 0.0660892 (438)	total: 9m 37s	remaining: 12m 18s
439:	learn: 0.0660989	test: 0.0660887	best: 0.0660887 (439)	total: 9m 39s	remaining: 12m 17s
440:	learn: 0.0660983	test: 0.0660880	best: 0.0660880 (440)	total: 9m 41s	remaining: 12m 16s
441:	learn: 0.0660977	test: 0.0660874	best: 0.0660874 (441)	total: 9m 42s	remaining: 12m 15s
442:	learn: 0.0660972	test: 0.0660869	best: 0.0660869 (442)	total: 9m 43s	remaining: 12m 13s
443:	learn: 0.0660966	test: 0.0660864	best: 0.0660864 (443)	total: 9m 44s	remaining: 12m 12s
444:	learn: 0.0660961	test: 0.0660859	best: 0.0660859 (444)	total: 9m 45s	remaining: 12m 10s
445:	learn: 0.0660957	test: 0.0660854	best: 0.0660854 (445)	total: 9m 47s	remaining: 12m 9s
446:	learn: 0.0660952	test: 0.0660850	best: 0.0660850 (446)	total: 9m 48s	remaining: 12m 7s
447:	learn: 0.0660947	test: 0.0660845	best: 0.0660845 (447)	total: 9m 48s	remaining: 12m 5s
448:	learn: 0.0660943	test: 0.0660840	best: 0.0660840 (448)	total: 9m 50s	remaining: 12m 4s
449:	learn: 0.0660936	test: 0.0660833	best: 0.0660833 (449)	total: 9m 51s	remaining: 12m 3s
450:	learn: 0.0660933	test: 0.0660831	best: 0.0660831 (450)	total: 9m 52s	remaining: 12m 1s
451:	learn: 0.0660922	test: 0.0660826	best: 0.0660826 (451)	total: 9m 54s	remaining: 12m
452:	learn: 0.0660917	test: 0.0660822	best: 0.0660822 (452)	total: 9m 54s	remaining: 11m 58s
453:	learn: 0.0660913	test: 0.0660817	best: 0.0660817 (453)	total: 9m 55s	remaining: 11m 56s
454:	learn: 0.0660908	test: 0.0660812	best: 0.0660812 (454)	total: 9m 56s	remaining: 11m 54s
455:	learn: 0.0660903	test: 0.0660806	best: 0.0660806 (455)	total: 9m 58s	remaining: 11m 53s
456:	learn: 0.0660896	test: 0.0660803	best: 0.0660803 (456)	total: 9m 59s	remaining: 11m 52s
457:	learn: 0.0660892	test: 0.0660799	best: 0.0660799 (457)	total: 10m	remaining: 11m 51s
458:	learn: 0.0660889	test: 0.0660797	best: 0.0660797 (458)	total: 10m 2s	remaining: 11m 49s
459:	learn: 0.0660881	test: 0.0660791	best: 0.0660791 (459)	total: 10m 3s	remaining: 11m 48s
460:	learn: 0.0660873	test: 0.0660785	best: 0.0660785 (460)	total: 10m 5s	remaining: 11m 47s
461:	learn: 0.0660865	test: 0.0660777	best: 0.0660777 (461)	total: 10m 6s	remaining: 11m 46s
462:	learn: 0.0660859	test: 0.0660771	best: 0.0660771 (462)	total: 10m 8s	remaining: 11m 45s
463:	learn: 0.0660853	test: 0.0660767	best: 0.0660767 (463)	total: 10m 9s	remaining: 11m 44s
464:	learn: 0.0660847	test: 0.0660761	best: 0.0660761 (464)	total: 10m 11s	remaining: 11m 43s
465:	learn: 0.0660838	test: 0.0660755	best: 0.0660755 (465)	total: 10m 13s	remaining: 11m 42s
466:	learn: 0.0660834	test: 0.0660751	best: 0.0660751 (466)	total: 10m 14s	remaining: 11m 41s
467:	learn: 0.0660830	test: 0.0660749	best: 0.0660749 (467)	total: 10m 15s	remaining: 11m 40s
468:	learn: 0.0660827	test: 0.0660747	best: 0.0660747 (468)	total: 10m 16s	remaining: 11m 38s
469:	learn: 0.0660821	test: 0.0660742	best: 0.0660742 (469)	total: 10m 18s	remaining: 11m 37s
470:	learn: 0.0660818	test: 0.0660740	best: 0.0660740 (470)	total: 10m 18s	remaining: 11m 35s
471:	learn: 0.0660815	test: 0.0660736	best: 0.0660736 (471)	total: 10m 19s	remaining: 11m 33s
472:	learn: 0.0660808	test: 0.0660732	best: 0.0660732 (472)	total: 10m 21s	remaining: 11m 32s
473:	learn: 0.0660805	test: 0.0660729	best: 0.0660729 (473)	total: 10m 22s	remaining: 11m 30s
474:	learn: 0.0660793	test: 0.0660723	best: 0.0660723 (474)	total: 10m 24s	remaining: 11m 29s
475:	learn: 0.0660788	test: 0.0660717	best: 0.0660717 (475)	total: 10m 25s	remaining: 11m 28s
476:	learn: 0.0660783	test: 0.0660714	best: 0.0660714 (476)	total: 10m 26s	remaining: 11m 27s
477:	learn: 0.0660778	test: 0.0660709	best: 0.0660709 (477)	total: 10m 28s	remaining: 11m 26s
478:	learn: 0.0660776	test: 0.0660708	best: 0.0660708 (478)	total: 10m 29s	remaining: 11m 25s
479:	learn: 0.0660767	test: 0.0660702	best: 0.0660702 (479)	total: 10m 31s	remaining: 11m 23s
480:	learn: 0.0660764	test: 0.0660698	best: 0.0660698 (480)	total: 10m 32s	remaining: 11m 22s
481:	learn: 0.0660757	test: 0.0660698	best: 0.0660698 (481)	total: 10m 34s	remaining: 11m 21s
482:	learn: 0.0660754	test: 0.0660696	best: 0.0660696 (482)	total: 10m 35s	remaining: 11m 19s
483:	learn: 0.0660751	test: 0.0660693	best: 0.0660693 (483)	total: 10m 36s	remaining: 11m 18s
484:	learn: 0.0660747	test: 0.0660689	best: 0.0660689 (484)	total: 10m 37s	remaining: 11m 16s
485:	learn: 0.0660745	test: 0.0660687	best: 0.0660687 (485)	total: 10m 38s	remaining: 11m 15s
486:	learn: 0.0660744	test: 0.0660686	best: 0.0660686 (486)	total: 10m 39s	remaining: 11m 13s
487:	learn: 0.0660742	test: 0.0660684	best: 0.0660684 (487)	total: 10m 40s	remaining: 11m 11s
488:	learn: 0.0660739	test: 0.0660681	best: 0.0660681 (488)	total: 10m 41s	remaining: 11m 10s
489:	learn: 0.0660734	test: 0.0660676	best: 0.0660676 (489)	total: 10m 42s	remaining: 11m 8s
490:	learn: 0.0660731	test: 0.0660673	best: 0.0660673 (490)	total: 10m 44s	remaining: 11m 7s
491:	learn: 0.0660726	test: 0.0660669	best: 0.0660669 (491)	total: 10m 45s	remaining: 11m 6s
492:	learn: 0.0660724	test: 0.0660667	best: 0.0660667 (492)	total: 10m 46s	remaining: 11m 5s
493:	learn: 0.0660721	test: 0.0660665	best: 0.0660665 (493)	total: 10m 47s	remaining: 11m 3s
494:	learn: 0.0660718	test: 0.0660662	best: 0.0660662 (494)	total: 10m 48s	remaining: 11m 2s
495:	learn: 0.0660713	test: 0.0660658	best: 0.0660658 (495)	total: 10m 50s	remaining: 11m 1s
496:	learn: 0.0660709	test: 0.0660655	best: 0.0660655 (496)	total: 10m 52s	remaining: 11m
497:	learn: 0.0660707	test: 0.0660653	best: 0.0660653 (497)	total: 10m 53s	remaining: 10m 58s
498:	learn: 0.0660706	test: 0.0660652	best: 0.0660652 (498)	total: 10m 53s	remaining: 10m 56s
499:	learn: 0.0660705	test: 0.0660651	best: 0.0660651 (499)	total: 10m 54s	remaining: 10m 54s
500:	learn: 0.0660698	test: 0.0660646	best: 0.0660646 (500)	total: 10m 55s	remaining: 10m 53s
501:	learn: 0.0660695	test: 0.0660644	best: 0.0660644 (501)	total: 10m 57s	remaining: 10m 52s
502:	learn: 0.0660694	test: 0.0660644	best: 0.0660644 (502)	total: 10m 58s	remaining: 10m 50s
503:	learn: 0.0660691	test: 0.0660641	best: 0.0660641 (503)	total: 10m 59s	remaining: 10m 49s
504:	learn: 0.0660689	test: 0.0660638	best: 0.0660638 (504)	total: 11m	remaining: 10m 47s
505:	learn: 0.0660687	test: 0.0660636	best: 0.0660636 (505)	total: 11m 1s	remaining: 10m 46s
506:	learn: 0.0660683	test: 0.0660635	best: 0.0660635 (506)	total: 11m 3s	remaining: 10m 44s
507:	learn: 0.0660680	test: 0.0660632	best: 0.0660632 (507)	total: 11m 4s	remaining: 10m 43s
508:	learn: 0.0660676	test: 0.0660630	best: 0.0660630 (508)	total: 11m 6s	remaining: 10m 42s
509:	learn: 0.0660674	test: 0.0660627	best: 0.0660627 (509)	total: 11m 7s	remaining: 10m 41s
510:	learn: 0.0660672	test: 0.0660625	best: 0.0660625 (510)	total: 11m 8s	remaining: 10m 39s
511:	learn: 0.0660669	test: 0.0660623	best: 0.0660623 (511)	total: 11m 9s	remaining: 10m 38s
512:	learn: 0.0660668	test: 0.0660621	best: 0.0660621 (512)	total: 11m 10s	remaining: 10m 36s
513:	learn: 0.0660667	test: 0.0660621	best: 0.0660621 (513)	total: 11m 11s	remaining: 10m 34s
514:	learn: 0.0660664	test: 0.0660617	best: 0.0660617 (514)	total: 11m 12s	remaining: 10m 33s
515:	learn: 0.0660663	test: 0.0660617	best: 0.0660617 (515)	total: 11m 13s	remaining: 10m 31s
516:	learn: 0.0660661	test: 0.0660614	best: 0.0660614 (516)	total: 11m 14s	remaining: 10m 30s
517:	learn: 0.0660653	test: 0.0660612	best: 0.0660612 (517)	total: 11m 16s	remaining: 10m 29s
518:	learn: 0.0660652	test: 0.0660610	best: 0.0660610 (518)	total: 11m 17s	remaining: 10m 27s
519:	learn: 0.0660646	test: 0.0660608	best: 0.0660608 (519)	total: 11m 18s	remaining: 10m 26s
520:	learn: 0.0660645	test: 0.0660607	best: 0.0660607 (520)	total: 11m 19s	remaining: 10m 24s
521:	learn: 0.0660643	test: 0.0660604	best: 0.0660604 (521)	total: 11m 20s	remaining: 10m 23s
522:	learn: 0.0660640	test: 0.0660602	best: 0.0660602 (522)	total: 11m 22s	remaining: 10m 22s
523:	learn: 0.0660635	test: 0.0660602	best: 0.0660602 (522)	total: 11m 24s	remaining: 10m 21s
524:	learn: 0.0660633	test: 0.0660601	best: 0.0660601 (524)	total: 11m 25s	remaining: 10m 20s
525:	learn: 0.0660630	test: 0.0660597	best: 0.0660597 (525)	total: 11m 26s	remaining: 10m 18s
526:	learn: 0.0660629	test: 0.0660597	best: 0.0660597 (526)	total: 11m 27s	remaining: 10m 17s
527:	learn: 0.0660627	test: 0.0660594	best: 0.0660594 (527)	total: 11m 28s	remaining: 10m 15s
528:	learn: 0.0660621	test: 0.0660592	best: 0.0660592 (528)	total: 11m 30s	remaining: 10m 14s
529:	learn: 0.0660618	test: 0.0660588	best: 0.0660588 (529)	total: 11m 31s	remaining: 10m 13s
530:	learn: 0.0660613	test: 0.0660586	best: 0.0660586 (530)	total: 11m 33s	remaining: 10m 12s
531:	learn: 0.0660607	test: 0.0660581	best: 0.0660581 (531)	total: 11m 34s	remaining: 10m 11s
532:	learn: 0.0660604	test: 0.0660579	best: 0.0660579 (532)	total: 11m 36s	remaining: 10m 10s
533:	learn: 0.0660603	test: 0.0660579	best: 0.0660579 (533)	total: 11m 37s	remaining: 10m 8s
534:	learn: 0.0660602	test: 0.0660578	best: 0.0660578 (534)	total: 11m 38s	remaining: 10m 7s
535:	learn: 0.0660601	test: 0.0660577	best: 0.0660577 (535)	total: 11m 39s	remaining: 10m 5s
536:	learn: 0.0660599	test: 0.0660577	best: 0.0660577 (536)	total: 11m 40s	remaining: 10m 4s
537:	learn: 0.0660598	test: 0.0660576	best: 0.0660576 (537)	total: 11m 41s	remaining: 10m 2s
538:	learn: 0.0660597	test: 0.0660575	best: 0.0660575 (538)	total: 11m 42s	remaining: 10m
539:	learn: 0.0660597	test: 0.0660575	best: 0.0660575 (539)	total: 11m 43s	remaining: 9m 58s
540:	learn: 0.0660590	test: 0.0660576	best: 0.0660575 (539)	total: 11m 44s	remaining: 9m 58s
541:	learn: 0.0660589	test: 0.0660576	best: 0.0660575 (539)	total: 11m 45s	remaining: 9m 56s
542:	learn: 0.0660589	test: 0.0660576	best: 0.0660575 (539)	total: 11m 46s	remaining: 9m 54s
543:	learn: 0.0660586	test: 0.0660575	best: 0.0660575 (543)	total: 11m 47s	remaining: 9m 53s
544:	learn: 0.0660586	test: 0.0660575	best: 0.0660575 (543)	total: 11m 48s	remaining: 9m 51s
545:	learn: 0.0660581	test: 0.0660573	best: 0.0660573 (545)	total: 11m 49s	remaining: 9m 49s
546:	learn: 0.0660580	test: 0.0660571	best: 0.0660571 (546)	total: 11m 51s	remaining: 9m 48s
547:	learn: 0.0660578	test: 0.0660570	best: 0.0660570 (547)	total: 11m 52s	remaining: 9m 47s
548:	learn: 0.0660576	test: 0.0660569	best: 0.0660569 (548)	total: 11m 53s	remaining: 9m 46s
549:	learn: 0.0660572	test: 0.0660567	best: 0.0660567 (549)	total: 11m 54s	remaining: 9m 44s
550:	learn: 0.0660571	test: 0.0660565	best: 0.0660565 (550)	total: 11m 55s	remaining: 9m 43s
551:	learn: 0.0660570	test: 0.0660563	best: 0.0660563 (551)	total: 11m 56s	remaining: 9m 41s
552:	learn: 0.0660568	test: 0.0660562	best: 0.0660562 (552)	total: 11m 58s	remaining: 9m 40s
553:	learn: 0.0660562	test: 0.0660561	best: 0.0660561 (553)	total: 11m 59s	remaining: 9m 39s
554:	learn: 0.0660561	test: 0.0660560	best: 0.0660560 (554)	total: 12m	remaining: 9m 37s
555:	learn: 0.0660560	test: 0.0660559	best: 0.0660559 (555)	total: 12m 1s	remaining: 9m 36s
556:	learn: 0.0660556	test: 0.0660559	best: 0.0660559 (556)	total: 12m 3s	remaining: 9m 35s
557:	learn: 0.0660554	test: 0.0660558	best: 0.0660558 (557)	total: 12m 4s	remaining: 9m 33s
558:	learn: 0.0660553	test: 0.0660557	best: 0.0660557 (558)	total: 12m 5s	remaining: 9m 32s
559:	learn: 0.0660551	test: 0.0660555	best: 0.0660555 (559)	total: 12m 7s	remaining: 9m 31s
560:	learn: 0.0660548	test: 0.0660555	best: 0.0660555 (559)	total: 12m 8s	remaining: 9m 30s
561:	learn: 0.0660548	test: 0.0660555	best: 0.0660555 (561)	total: 12m 9s	remaining: 9m 28s
562:	learn: 0.0660546	test: 0.0660553	best: 0.0660553 (562)	total: 12m 11s	remaining: 9m 27s
563:	learn: 0.0660545	test: 0.0660552	best: 0.0660552 (563)	total: 12m 12s	remaining: 9m 25s
564:	learn: 0.0660544	test: 0.0660550	best: 0.0660550 (564)	total: 12m 13s	remaining: 9m 24s
565:	learn: 0.0660540	test: 0.0660550	best: 0.0660550 (564)	total: 12m 14s	remaining: 9m 23s
566:	learn: 0.0660538	test: 0.0660548	best: 0.0660548 (566)	total: 12m 16s	remaining: 9m 22s
567:	learn: 0.0660536	test: 0.0660547	best: 0.0660547 (567)	total: 12m 17s	remaining: 9m 20s
568:	learn: 0.0660535	test: 0.0660546	best: 0.0660546 (568)	total: 12m 18s	remaining: 9m 19s
569:	learn: 0.0660532	test: 0.0660544	best: 0.0660544 (569)	total: 12m 20s	remaining: 9m 18s
570:	learn: 0.0660531	test: 0.0660543	best: 0.0660543 (570)	total: 12m 20s	remaining: 9m 16s
571:	learn: 0.0660530	test: 0.0660541	best: 0.0660541 (571)	total: 12m 21s	remaining: 9m 14s
572:	learn: 0.0660529	test: 0.0660540	best: 0.0660540 (572)	total: 12m 22s	remaining: 9m 13s
573:	learn: 0.0660525	test: 0.0660538	best: 0.0660538 (573)	total: 12m 23s	remaining: 9m 12s
574:	learn: 0.0660523	test: 0.0660537	best: 0.0660537 (574)	total: 12m 25s	remaining: 9m 10s
575:	learn: 0.0660521	test: 0.0660535	best: 0.0660535 (575)	total: 12m 26s	remaining: 9m 9s
576:	learn: 0.0660516	test: 0.0660534	best: 0.0660534 (576)	total: 12m 28s	remaining: 9m 8s
577:	learn: 0.0660515	test: 0.0660533	best: 0.0660533 (577)	total: 12m 29s	remaining: 9m 7s
578:	learn: 0.0660515	test: 0.0660532	best: 0.0660532 (578)	total: 12m 30s	remaining: 9m 5s
579:	learn: 0.0660514	test: 0.0660531	best: 0.0660531 (579)	total: 12m 31s	remaining: 9m 4s
580:	learn: 0.0660509	test: 0.0660534	best: 0.0660531 (579)	total: 12m 33s	remaining: 9m 3s
581:	learn: 0.0660509	test: 0.0660534	best: 0.0660531 (579)	total: 12m 34s	remaining: 9m 1s
582:	learn: 0.0660506	test: 0.0660533	best: 0.0660531 (579)	total: 12m 35s	remaining: 9m
583:	learn: 0.0660506	test: 0.0660534	best: 0.0660531 (579)	total: 12m 36s	remaining: 8m 59s
584:	learn: 0.0660503	test: 0.0660533	best: 0.0660531 (579)	total: 12m 38s	remaining: 8m 57s
585:	learn: 0.0660502	test: 0.0660532	best: 0.0660531 (579)	total: 12m 39s	remaining: 8m 56s
586:	learn: 0.0660501	test: 0.0660532	best: 0.0660531 (579)	total: 12m 40s	remaining: 8m 54s
587:	learn: 0.0660500	test: 0.0660531	best: 0.0660531 (587)	total: 12m 41s	remaining: 8m 53s
588:	learn: 0.0660498	test: 0.0660531	best: 0.0660531 (587)	total: 12m 42s	remaining: 8m 52s
589:	learn: 0.0660495	test: 0.0660531	best: 0.0660531 (587)	total: 12m 44s	remaining: 8m 51s
590:	learn: 0.0660491	test: 0.0660530	best: 0.0660530 (590)	total: 12m 46s	remaining: 8m 50s
591:	learn: 0.0660490	test: 0.0660529	best: 0.0660529 (591)	total: 12m 47s	remaining: 8m 48s
592:	learn: 0.0660487	test: 0.0660528	best: 0.0660528 (592)	total: 12m 49s	remaining: 8m 47s
593:	learn: 0.0660484	test: 0.0660527	best: 0.0660527 (593)	total: 12m 50s	remaining: 8m 46s
594:	learn: 0.0660481	test: 0.0660526	best: 0.0660526 (594)	total: 12m 51s	remaining: 8m 45s
595:	learn: 0.0660481	test: 0.0660526	best: 0.0660526 (595)	total: 12m 53s	remaining: 8m 44s
596:	learn: 0.0660479	test: 0.0660525	best: 0.0660525 (596)	total: 12m 54s	remaining: 8m 42s
597:	learn: 0.0660477	test: 0.0660525	best: 0.0660525 (596)	total: 12m 56s	remaining: 8m 41s
598:	learn: 0.0660471	test: 0.0660525	best: 0.0660525 (598)	total: 12m 57s	remaining: 8m 40s
599:	learn: 0.0660467	test: 0.0660524	best: 0.0660524 (599)	total: 12m 59s	remaining: 8m 39s
600:	learn: 0.0660466	test: 0.0660523	best: 0.0660523 (600)	total: 13m	remaining: 8m 38s
601:	learn: 0.0660464	test: 0.0660522	best: 0.0660522 (601)	total: 13m 2s	remaining: 8m 37s
602:	learn: 0.0660463	test: 0.0660520	best: 0.0660520 (602)	total: 13m 3s	remaining: 8m 36s
603:	learn: 0.0660461	test: 0.0660519	best: 0.0660519 (603)	total: 13m 4s	remaining: 8m 34s
604:	learn: 0.0660459	test: 0.0660520	best: 0.0660519 (603)	total: 13m 6s	remaining: 8m 33s
605:	learn: 0.0660458	test: 0.0660520	best: 0.0660519 (603)	total: 13m 7s	remaining: 8m 31s
606:	learn: 0.0660457	test: 0.0660519	best: 0.0660519 (603)	total: 13m 9s	remaining: 8m 30s
607:	learn: 0.0660455	test: 0.0660518	best: 0.0660518 (607)	total: 13m 10s	remaining: 8m 29s
608:	learn: 0.0660453	test: 0.0660517	best: 0.0660517 (608)	total: 13m 12s	remaining: 8m 28s
609:	learn: 0.0660450	test: 0.0660516	best: 0.0660516 (609)	total: 13m 13s	remaining: 8m 27s
610:	learn: 0.0660448	test: 0.0660515	best: 0.0660515 (610)	total: 13m 15s	remaining: 8m 26s
611:	learn: 0.0660448	test: 0.0660515	best: 0.0660515 (611)	total: 13m 16s	remaining: 8m 24s
612:	learn: 0.0660448	test: 0.0660514	best: 0.0660514 (612)	total: 13m 16s	remaining: 8m 23s
613:	learn: 0.0660444	test: 0.0660518	best: 0.0660514 (612)	total: 13m 18s	remaining: 8m 21s
614:	learn: 0.0660441	test: 0.0660517	best: 0.0660514 (612)	total: 13m 19s	remaining: 8m 20s
615:	learn: 0.0660439	test: 0.0660515	best: 0.0660514 (612)	total: 13m 21s	remaining: 8m 19s
616:	learn: 0.0660438	test: 0.0660516	best: 0.0660514 (612)	total: 13m 22s	remaining: 8m 18s
617:	learn: 0.0660436	test: 0.0660515	best: 0.0660514 (612)	total: 13m 23s	remaining: 8m 16s
618:	learn: 0.0660433	test: 0.0660515	best: 0.0660514 (612)	total: 13m 25s	remaining: 8m 15s
619:	learn: 0.0660433	test: 0.0660515	best: 0.0660514 (612)	total: 13m 26s	remaining: 8m 14s
620:	learn: 0.0660432	test: 0.0660515	best: 0.0660514 (612)	total: 13m 27s	remaining: 8m 12s
621:	learn: 0.0660427	test: 0.0660518	best: 0.0660514 (612)	total: 13m 29s	remaining: 8m 11s
622:	learn: 0.0660426	test: 0.0660518	best: 0.0660514 (612)	total: 13m 30s	remaining: 8m 10s
623:	learn: 0.0660424	test: 0.0660516	best: 0.0660514 (612)	total: 13m 32s	remaining: 8m 9s
624:	learn: 0.0660423	test: 0.0660515	best: 0.0660514 (612)	total: 13m 33s	remaining: 8m 8s
625:	learn: 0.0660422	test: 0.0660515	best: 0.0660514 (612)	total: 13m 34s	remaining: 8m 6s
626:	learn: 0.0660418	test: 0.0660515	best: 0.0660514 (612)	total: 13m 35s	remaining: 8m 5s
627:	learn: 0.0660417	test: 0.0660513	best: 0.0660513 (627)	total: 13m 37s	remaining: 8m 4s
628:	learn: 0.0660413	test: 0.0660515	best: 0.0660513 (627)	total: 13m 38s	remaining: 8m 3s
629:	learn: 0.0660411	test: 0.0660516	best: 0.0660513 (627)	total: 13m 40s	remaining: 8m 2s
630:	learn: 0.0660408	test: 0.0660514	best: 0.0660513 (627)	total: 13m 42s	remaining: 8m
631:	learn: 0.0660408	test: 0.0660514	best: 0.0660513 (627)	total: 13m 42s	remaining: 7m 59s
632:	learn: 0.0660407	test: 0.0660514	best: 0.0660513 (627)	total: 13m 43s	remaining: 7m 57s
633:	learn: 0.0660407	test: 0.0660515	best: 0.0660513 (627)	total: 13m 44s	remaining: 7m 55s
634:	learn: 0.0660406	test: 0.0660514	best: 0.0660513 (627)	total: 13m 46s	remaining: 7m 54s
635:	learn: 0.0660399	test: 0.0660514	best: 0.0660513 (627)	total: 13m 47s	remaining: 7m 53s
636:	learn: 0.0660398	test: 0.0660514	best: 0.0660513 (627)	total: 13m 49s	remaining: 7m 52s
637:	learn: 0.0660394	test: 0.0660514	best: 0.0660513 (627)	total: 13m 51s	remaining: 7m 51s
638:	learn: 0.0660391	test: 0.0660512	best: 0.0660512 (638)	total: 13m 52s	remaining: 7m 50s
639:	learn: 0.0660388	test: 0.0660511	best: 0.0660511 (639)	total: 13m 54s	remaining: 7m 49s
640:	learn: 0.0660387	test: 0.0660511	best: 0.0660511 (640)	total: 13m 55s	remaining: 7m 48s
641:	learn: 0.0660386	test: 0.0660510	best: 0.0660510 (641)	total: 13m 56s	remaining: 7m 46s
642:	learn: 0.0660386	test: 0.0660509	best: 0.0660509 (642)	total: 13m 57s	remaining: 7m 45s
643:	learn: 0.0660384	test: 0.0660508	best: 0.0660508 (643)	total: 13m 58s	remaining: 7m 43s
644:	learn: 0.0660382	test: 0.0660507	best: 0.0660507 (644)	total: 14m	remaining: 7m 42s
645:	learn: 0.0660382	test: 0.0660507	best: 0.0660507 (644)	total: 14m 1s	remaining: 7m 41s
646:	learn: 0.0660381	test: 0.0660507	best: 0.0660507 (646)	total: 14m 2s	remaining: 7m 39s
647:	learn: 0.0660381	test: 0.0660506	best: 0.0660506 (647)	total: 14m 3s	remaining: 7m 38s
648:	learn: 0.0660380	test: 0.0660505	best: 0.0660505 (648)	total: 14m 5s	remaining: 7m 37s
649:	learn: 0.0660379	test: 0.0660506	best: 0.0660505 (648)	total: 14m 6s	remaining: 7m 35s
650:	learn: 0.0660379	test: 0.0660506	best: 0.0660505 (648)	total: 14m 7s	remaining: 7m 34s
651:	learn: 0.0660378	test: 0.0660505	best: 0.0660505 (651)	total: 14m 8s	remaining: 7m 32s
652:	learn: 0.0660377	test: 0.0660505	best: 0.0660505 (652)	total: 14m 9s	remaining: 7m 31s
653:	learn: 0.0660375	test: 0.0660504	best: 0.0660504 (653)	total: 14m 11s	remaining: 7m 30s
654:	learn: 0.0660370	test: 0.0660504	best: 0.0660504 (653)	total: 14m 13s	remaining: 7m 29s
655:	learn: 0.0660369	test: 0.0660504	best: 0.0660504 (655)	total: 14m 13s	remaining: 7m 27s
656:	learn: 0.0660367	test: 0.0660504	best: 0.0660504 (655)	total: 14m 15s	remaining: 7m 26s
657:	learn: 0.0660366	test: 0.0660504	best: 0.0660504 (657)	total: 14m 16s	remaining: 7m 25s
658:	learn: 0.0660365	test: 0.0660503	best: 0.0660503 (658)	total: 14m 17s	remaining: 7m 23s
659:	learn: 0.0660365	test: 0.0660503	best: 0.0660503 (659)	total: 14m 18s	remaining: 7m 22s
660:	learn: 0.0660364	test: 0.0660503	best: 0.0660503 (660)	total: 14m 19s	remaining: 7m 20s
661:	learn: 0.0660361	test: 0.0660500	best: 0.0660500 (661)	total: 14m 21s	remaining: 7m 19s
662:	learn: 0.0660361	test: 0.0660501	best: 0.0660500 (661)	total: 14m 22s	remaining: 7m 18s
663:	learn: 0.0660361	test: 0.0660501	best: 0.0660500 (661)	total: 14m 22s	remaining: 7m 16s
664:	learn: 0.0660361	test: 0.0660500	best: 0.0660500 (664)	total: 14m 23s	remaining: 7m 14s
665:	learn: 0.0660360	test: 0.0660500	best: 0.0660500 (665)	total: 14m 24s	remaining: 7m 13s
666:	learn: 0.0660359	test: 0.0660500	best: 0.0660500 (665)	total: 14m 25s	remaining: 7m 12s
667:	learn: 0.0660354	test: 0.0660501	best: 0.0660500 (665)	total: 14m 27s	remaining: 7m 11s
668:	learn: 0.0660354	test: 0.0660500	best: 0.0660500 (665)	total: 14m 28s	remaining: 7m 9s
669:	learn: 0.0660349	test: 0.0660503	best: 0.0660500 (665)	total: 14m 30s	remaining: 7m 8s
670:	learn: 0.0660344	test: 0.0660502	best: 0.0660500 (665)	total: 14m 32s	remaining: 7m 7s
671:	learn: 0.0660343	test: 0.0660501	best: 0.0660500 (665)	total: 14m 33s	remaining: 7m 6s
672:	learn: 0.0660343	test: 0.0660501	best: 0.0660500 (665)	total: 14m 33s	remaining: 7m 4s
673:	learn: 0.0660342	test: 0.0660501	best: 0.0660500 (665)	total: 14m 35s	remaining: 7m 3s
674:	learn: 0.0660339	test: 0.0660499	best: 0.0660499 (674)	total: 14m 36s	remaining: 7m 2s
675:	learn: 0.0660337	test: 0.0660499	best: 0.0660499 (675)	total: 14m 38s	remaining: 7m
676:	learn: 0.0660333	test: 0.0660499	best: 0.0660499 (676)	total: 14m 39s	remaining: 6m 59s
677:	learn: 0.0660333	test: 0.0660499	best: 0.0660499 (677)	total: 14m 40s	remaining: 6m 58s
678:	learn: 0.0660332	test: 0.0660498	best: 0.0660498 (678)	total: 14m 42s	remaining: 6m 57s
679:	learn: 0.0660332	test: 0.0660497	best: 0.0660497 (679)	total: 14m 43s	remaining: 6m 55s
680:	learn: 0.0660328	test: 0.0660498	best: 0.0660497 (679)	total: 14m 45s	remaining: 6m 54s
681:	learn: 0.0660326	test: 0.0660497	best: 0.0660497 (681)	total: 14m 46s	remaining: 6m 53s
682:	learn: 0.0660321	test: 0.0660495	best: 0.0660495 (682)	total: 14m 48s	remaining: 6m 52s
683:	learn: 0.0660321	test: 0.0660495	best: 0.0660495 (683)	total: 14m 48s	remaining: 6m 50s
684:	learn: 0.0660321	test: 0.0660495	best: 0.0660495 (684)	total: 14m 49s	remaining: 6m 49s
685:	learn: 0.0660319	test: 0.0660496	best: 0.0660495 (684)	total: 14m 51s	remaining: 6m 47s
686:	learn: 0.0660319	test: 0.0660496	best: 0.0660495 (684)	total: 14m 52s	remaining: 6m 46s
687:	learn: 0.0660317	test: 0.0660495	best: 0.0660495 (687)	total: 14m 54s	remaining: 6m 45s
688:	learn: 0.0660316	test: 0.0660494	best: 0.0660494 (688)	total: 14m 55s	remaining: 6m 44s
689:	learn: 0.0660316	test: 0.0660493	best: 0.0660493 (689)	total: 14m 55s	remaining: 6m 42s
690:	learn: 0.0660315	test: 0.0660493	best: 0.0660493 (690)	total: 14m 56s	remaining: 6m 40s
691:	learn: 0.0660313	test: 0.0660490	best: 0.0660490 (691)	total: 14m 58s	remaining: 6m 39s
692:	learn: 0.0660312	test: 0.0660490	best: 0.0660490 (691)	total: 14m 59s	remaining: 6m 38s
693:	learn: 0.0660309	test: 0.0660489	best: 0.0660489 (693)	total: 15m 1s	remaining: 6m 37s
694:	learn: 0.0660307	test: 0.0660489	best: 0.0660489 (693)	total: 15m 2s	remaining: 6m 36s
695:	learn: 0.0660304	test: 0.0660488	best: 0.0660488 (695)	total: 15m 4s	remaining: 6m 34s
696:	learn: 0.0660300	test: 0.0660490	best: 0.0660488 (695)	total: 15m 5s	remaining: 6m 33s
697:	learn: 0.0660296	test: 0.0660490	best: 0.0660488 (695)	total: 15m 7s	remaining: 6m 32s
698:	learn: 0.0660295	test: 0.0660489	best: 0.0660488 (695)	total: 15m 9s	remaining: 6m 31s
699:	learn: 0.0660291	test: 0.0660489	best: 0.0660488 (695)	total: 15m 11s	remaining: 6m 30s
700:	learn: 0.0660290	test: 0.0660489	best: 0.0660488 (695)	total: 15m 12s	remaining: 6m 29s
701:	learn: 0.0660290	test: 0.0660489	best: 0.0660488 (695)	total: 15m 13s	remaining: 6m 27s
702:	learn: 0.0660290	test: 0.0660489	best: 0.0660488 (695)	total: 15m 14s	remaining: 6m 26s
703:	learn: 0.0660289	test: 0.0660489	best: 0.0660488 (695)	total: 15m 15s	remaining: 6m 24s
704:	learn: 0.0660289	test: 0.0660488	best: 0.0660488 (695)	total: 15m 16s	remaining: 6m 23s
705:	learn: 0.0660285	test: 0.0660490	best: 0.0660488 (695)	total: 15m 18s	remaining: 6m 22s
706:	learn: 0.0660280	test: 0.0660490	best: 0.0660488 (695)	total: 15m 19s	remaining: 6m 21s
707:	learn: 0.0660277	test: 0.0660490	best: 0.0660488 (695)	total: 15m 21s	remaining: 6m 20s
708:	learn: 0.0660277	test: 0.0660490	best: 0.0660488 (695)	total: 15m 22s	remaining: 6m 18s
709:	learn: 0.0660271	test: 0.0660491	best: 0.0660488 (695)	total: 15m 24s	remaining: 6m 17s
710:	learn: 0.0660268	test: 0.0660492	best: 0.0660488 (695)	total: 15m 25s	remaining: 6m 16s
711:	learn: 0.0660267	test: 0.0660492	best: 0.0660488 (695)	total: 15m 26s	remaining: 6m 14s
712:	learn: 0.0660266	test: 0.0660492	best: 0.0660488 (695)	total: 15m 27s	remaining: 6m 13s
713:	learn: 0.0660266	test: 0.0660491	best: 0.0660488 (695)	total: 15m 29s	remaining: 6m 12s
714:	learn: 0.0660264	test: 0.0660490	best: 0.0660488 (695)	total: 15m 31s	remaining: 6m 11s
715:	learn: 0.0660262	test: 0.0660489	best: 0.0660488 (695)	total: 15m 32s	remaining: 6m 9s
716:	learn: 0.0660261	test: 0.0660488	best: 0.0660488 (695)	total: 15m 33s	remaining: 6m 8s
717:	learn: 0.0660261	test: 0.0660488	best: 0.0660488 (695)	total: 15m 35s	remaining: 6m 7s
718:	learn: 0.0660260	test: 0.0660488	best: 0.0660488 (695)	total: 15m 36s	remaining: 6m 6s
719:	learn: 0.0660257	test: 0.0660489	best: 0.0660488 (695)	total: 15m 38s	remaining: 6m 5s
720:	learn: 0.0660254	test: 0.0660489	best: 0.0660488 (695)	total: 15m 40s	remaining: 6m 3s
721:	learn: 0.0660253	test: 0.0660490	best: 0.0660488 (695)	total: 15m 41s	remaining: 6m 2s
722:	learn: 0.0660253	test: 0.0660490	best: 0.0660488 (695)	total: 15m 41s	remaining: 6m
723:	learn: 0.0660251	test: 0.0660490	best: 0.0660488 (695)	total: 15m 43s	remaining: 5m 59s
724:	learn: 0.0660249	test: 0.0660489	best: 0.0660488 (695)	total: 15m 44s	remaining: 5m 58s
725:	learn: 0.0660247	test: 0.0660488	best: 0.0660488 (725)	total: 15m 46s	remaining: 5m 57s
726:	learn: 0.0660247	test: 0.0660487	best: 0.0660487 (726)	total: 15m 47s	remaining: 5m 55s
727:	learn: 0.0660245	test: 0.0660487	best: 0.0660487 (727)	total: 15m 49s	remaining: 5m 54s
728:	learn: 0.0660242	test: 0.0660487	best: 0.0660487 (728)	total: 15m 51s	remaining: 5m 53s
729:	learn: 0.0660238	test: 0.0660485	best: 0.0660485 (729)	total: 15m 53s	remaining: 5m 52s
730:	learn: 0.0660237	test: 0.0660485	best: 0.0660485 (730)	total: 15m 54s	remaining: 5m 51s
731:	learn: 0.0660232	test: 0.0660483	best: 0.0660483 (731)	total: 15m 56s	remaining: 5m 50s
732:	learn: 0.0660231	test: 0.0660482	best: 0.0660482 (732)	total: 15m 56s	remaining: 5m 48s
733:	learn: 0.0660230	test: 0.0660481	best: 0.0660481 (733)	total: 15m 58s	remaining: 5m 47s
734:	learn: 0.0660229	test: 0.0660480	best: 0.0660480 (734)	total: 15m 59s	remaining: 5m 45s
735:	learn: 0.0660228	test: 0.0660481	best: 0.0660480 (734)	total: 16m 1s	remaining: 5m 44s
736:	learn: 0.0660226	test: 0.0660481	best: 0.0660480 (734)	total: 16m 2s	remaining: 5m 43s
737:	learn: 0.0660221	test: 0.0660480	best: 0.0660480 (737)	total: 16m 4s	remaining: 5m 42s
738:	learn: 0.0660221	test: 0.0660480	best: 0.0660480 (738)	total: 16m 5s	remaining: 5m 40s
739:	learn: 0.0660219	test: 0.0660479	best: 0.0660479 (739)	total: 16m 6s	remaining: 5m 39s
740:	learn: 0.0660219	test: 0.0660480	best: 0.0660479 (739)	total: 16m 7s	remaining: 5m 38s
741:	learn: 0.0660219	test: 0.0660479	best: 0.0660479 (741)	total: 16m 9s	remaining: 5m 37s
742:	learn: 0.0660216	test: 0.0660478	best: 0.0660478 (742)	total: 16m 11s	remaining: 5m 35s
743:	learn: 0.0660216	test: 0.0660478	best: 0.0660478 (742)	total: 16m 11s	remaining: 5m 34s
744:	learn: 0.0660215	test: 0.0660477	best: 0.0660477 (744)	total: 16m 12s	remaining: 5m 33s
745:	learn: 0.0660215	test: 0.0660477	best: 0.0660477 (745)	total: 16m 13s	remaining: 5m 31s
746:	learn: 0.0660215	test: 0.0660477	best: 0.0660477 (746)	total: 16m 14s	remaining: 5m 30s
747:	learn: 0.0660215	test: 0.0660477	best: 0.0660477 (747)	total: 16m 15s	remaining: 5m 28s
748:	learn: 0.0660214	test: 0.0660476	best: 0.0660476 (748)	total: 16m 16s	remaining: 5m 27s
749:	learn: 0.0660213	test: 0.0660476	best: 0.0660476 (749)	total: 16m 17s	remaining: 5m 25s
750:	learn: 0.0660213	test: 0.0660475	best: 0.0660475 (750)	total: 16m 18s	remaining: 5m 24s
751:	learn: 0.0660211	test: 0.0660475	best: 0.0660475 (751)	total: 16m 20s	remaining: 5m 23s
752:	learn: 0.0660210	test: 0.0660474	best: 0.0660474 (752)	total: 16m 21s	remaining: 5m 22s
753:	learn: 0.0660210	test: 0.0660473	best: 0.0660473 (753)	total: 16m 23s	remaining: 5m 20s
754:	learn: 0.0660208	test: 0.0660475	best: 0.0660473 (753)	total: 16m 24s	remaining: 5m 19s
755:	learn: 0.0660206	test: 0.0660475	best: 0.0660473 (753)	total: 16m 25s	remaining: 5m 18s
756:	learn: 0.0660204	test: 0.0660473	best: 0.0660473 (756)	total: 16m 27s	remaining: 5m 17s
757:	learn: 0.0660201	test: 0.0660474	best: 0.0660473 (756)	total: 16m 29s	remaining: 5m 15s
758:	learn: 0.0660201	test: 0.0660474	best: 0.0660473 (756)	total: 16m 29s	remaining: 5m 14s
759:	learn: 0.0660197	test: 0.0660472	best: 0.0660472 (759)	total: 16m 31s	remaining: 5m 13s
760:	learn: 0.0660197	test: 0.0660471	best: 0.0660471 (760)	total: 16m 32s	remaining: 5m 11s
761:	learn: 0.0660195	test: 0.0660470	best: 0.0660470 (761)	total: 16m 34s	remaining: 5m 10s
762:	learn: 0.0660190	test: 0.0660470	best: 0.0660470 (762)	total: 16m 35s	remaining: 5m 9s
763:	learn: 0.0660188	test: 0.0660469	best: 0.0660469 (763)	total: 16m 37s	remaining: 5m 8s
764:	learn: 0.0660187	test: 0.0660469	best: 0.0660469 (764)	total: 16m 38s	remaining: 5m 6s
765:	learn: 0.0660185	test: 0.0660469	best: 0.0660469 (764)	total: 16m 40s	remaining: 5m 5s
766:	learn: 0.0660185	test: 0.0660470	best: 0.0660469 (764)	total: 16m 42s	remaining: 5m 4s
767:	learn: 0.0660180	test: 0.0660470	best: 0.0660469 (764)	total: 16m 43s	remaining: 5m 3s
768:	learn: 0.0660180	test: 0.0660470	best: 0.0660469 (764)	total: 16m 45s	remaining: 5m 2s
769:	learn: 0.0660180	test: 0.0660470	best: 0.0660469 (764)	total: 16m 46s	remaining: 5m
770:	learn: 0.0660180	test: 0.0660470	best: 0.0660469 (764)	total: 16m 47s	remaining: 4m 59s
771:	learn: 0.0660178	test: 0.0660468	best: 0.0660468 (771)	total: 16m 48s	remaining: 4m 57s
772:	learn: 0.0660178	test: 0.0660468	best: 0.0660468 (772)	total: 16m 49s	remaining: 4m 56s
773:	learn: 0.0660177	test: 0.0660468	best: 0.0660468 (773)	total: 16m 51s	remaining: 4m 55s
774:	learn: 0.0660175	test: 0.0660469	best: 0.0660468 (773)	total: 16m 52s	remaining: 4m 53s
775:	learn: 0.0660175	test: 0.0660468	best: 0.0660468 (773)	total: 16m 52s	remaining: 4m 52s
776:	learn: 0.0660175	test: 0.0660468	best: 0.0660468 (773)	total: 16m 53s	remaining: 4m 50s
777:	learn: 0.0660173	test: 0.0660469	best: 0.0660468 (773)	total: 16m 54s	remaining: 4m 49s
778:	learn: 0.0660172	test: 0.0660468	best: 0.0660468 (773)	total: 16m 55s	remaining: 4m 48s
779:	learn: 0.0660172	test: 0.0660469	best: 0.0660468 (773)	total: 16m 56s	remaining: 4m 46s
780:	learn: 0.0660172	test: 0.0660468	best: 0.0660468 (773)	total: 16m 57s	remaining: 4m 45s
781:	learn: 0.0660171	test: 0.0660469	best: 0.0660468 (773)	total: 16m 58s	remaining: 4m 44s
782:	learn: 0.0660170	test: 0.0660470	best: 0.0660468 (773)	total: 17m	remaining: 4m 42s
783:	learn: 0.0660169	test: 0.0660469	best: 0.0660468 (773)	total: 17m 1s	remaining: 4m 41s
784:	learn: 0.0660169	test: 0.0660469	best: 0.0660468 (773)	total: 17m 2s	remaining: 4m 40s
785:	learn: 0.0660166	test: 0.0660468	best: 0.0660468 (785)	total: 17m 4s	remaining: 4m 38s
786:	learn: 0.0660166	test: 0.0660468	best: 0.0660468 (785)	total: 17m 5s	remaining: 4m 37s
787:	learn: 0.0660165	test: 0.0660468	best: 0.0660468 (787)	total: 17m 7s	remaining: 4m 36s
788:	learn: 0.0660165	test: 0.0660467	best: 0.0660467 (788)	total: 17m 7s	remaining: 4m 34s
789:	learn: 0.0660165	test: 0.0660468	best: 0.0660467 (788)	total: 17m 9s	remaining: 4m 33s
790:	learn: 0.0660163	test: 0.0660470	best: 0.0660467 (788)	total: 17m 11s	remaining: 4m 32s
791:	learn: 0.0660162	test: 0.0660469	best: 0.0660467 (788)	total: 17m 12s	remaining: 4m 31s
792:	learn: 0.0660162	test: 0.0660469	best: 0.0660467 (788)	total: 17m 13s	remaining: 4m 29s
793:	learn: 0.0660162	test: 0.0660469	best: 0.0660467 (788)	total: 17m 14s	remaining: 4m 28s
794:	learn: 0.0660160	test: 0.0660470	best: 0.0660467 (788)	total: 17m 16s	remaining: 4m 27s
795:	learn: 0.0660160	test: 0.0660470	best: 0.0660467 (788)	total: 17m 16s	remaining: 4m 25s
796:	learn: 0.0660160	test: 0.0660470	best: 0.0660467 (788)	total: 17m 17s	remaining: 4m 24s
797:	learn: 0.0660160	test: 0.0660470	best: 0.0660467 (788)	total: 17m 18s	remaining: 4m 22s
798:	learn: 0.0660156	test: 0.0660473	best: 0.0660467 (788)	total: 17m 20s	remaining: 4m 21s
799:	learn: 0.0660154	test: 0.0660474	best: 0.0660467 (788)	total: 17m 21s	remaining: 4m 20s
800:	learn: 0.0660153	test: 0.0660474	best: 0.0660467 (788)	total: 17m 22s	remaining: 4m 19s
801:	learn: 0.0660153	test: 0.0660474	best: 0.0660467 (788)	total: 17m 23s	remaining: 4m 17s
802:	learn: 0.0660153	test: 0.0660474	best: 0.0660467 (788)	total: 17m 24s	remaining: 4m 16s
803:	learn: 0.0660152	test: 0.0660473	best: 0.0660467 (788)	total: 17m 26s	remaining: 4m 15s
804:	learn: 0.0660149	test: 0.0660474	best: 0.0660467 (788)	total: 17m 27s	remaining: 4m 13s
805:	learn: 0.0660146	test: 0.0660474	best: 0.0660467 (788)	total: 17m 29s	remaining: 4m 12s
806:	learn: 0.0660145	test: 0.0660474	best: 0.0660467 (788)	total: 17m 29s	remaining: 4m 11s
807:	learn: 0.0660141	test: 0.0660474	best: 0.0660467 (788)	total: 17m 31s	remaining: 4m 9s
808:	learn: 0.0660140	test: 0.0660473	best: 0.0660467 (788)	total: 17m 32s	remaining: 4m 8s
809:	learn: 0.0660140	test: 0.0660473	best: 0.0660467 (788)	total: 17m 34s	remaining: 4m 7s
810:	learn: 0.0660137	test: 0.0660471	best: 0.0660467 (788)	total: 17m 35s	remaining: 4m 6s
811:	learn: 0.0660136	test: 0.0660471	best: 0.0660467 (788)	total: 17m 37s	remaining: 4m 4s
812:	learn: 0.0660136	test: 0.0660471	best: 0.0660467 (788)	total: 17m 38s	remaining: 4m 3s
813:	learn: 0.0660134	test: 0.0660471	best: 0.0660467 (788)	total: 17m 39s	remaining: 4m 2s
814:	learn: 0.0660128	test: 0.0660473	best: 0.0660467 (788)	total: 17m 41s	remaining: 4m
815:	learn: 0.0660127	test: 0.0660472	best: 0.0660467 (788)	total: 17m 42s	remaining: 3m 59s
816:	learn: 0.0660126	test: 0.0660472	best: 0.0660467 (788)	total: 17m 44s	remaining: 3m 58s
817:	learn: 0.0660125	test: 0.0660471	best: 0.0660467 (788)	total: 17m 45s	remaining: 3m 56s
818:	learn: 0.0660124	test: 0.0660471	best: 0.0660467 (788)	total: 17m 45s	remaining: 3m 55s
819:	learn: 0.0660124	test: 0.0660471	best: 0.0660467 (788)	total: 17m 46s	remaining: 3m 54s
820:	learn: 0.0660121	test: 0.0660470	best: 0.0660467 (788)	total: 17m 48s	remaining: 3m 52s
821:	learn: 0.0660121	test: 0.0660470	best: 0.0660467 (788)	total: 17m 49s	remaining: 3m 51s
822:	learn: 0.0660120	test: 0.0660470	best: 0.0660467 (788)	total: 17m 50s	remaining: 3m 50s
823:	learn: 0.0660120	test: 0.0660471	best: 0.0660467 (788)	total: 17m 51s	remaining: 3m 48s
824:	learn: 0.0660119	test: 0.0660471	best: 0.0660467 (788)	total: 17m 52s	remaining: 3m 47s
825:	learn: 0.0660119	test: 0.0660471	best: 0.0660467 (788)	total: 17m 53s	remaining: 3m 46s
826:	learn: 0.0660119	test: 0.0660471	best: 0.0660467 (788)	total: 17m 54s	remaining: 3m 44s
827:	learn: 0.0660119	test: 0.0660471	best: 0.0660467 (788)	total: 17m 55s	remaining: 3m 43s
828:	learn: 0.0660119	test: 0.0660471	best: 0.0660467 (788)	total: 17m 56s	remaining: 3m 42s
829:	learn: 0.0660119	test: 0.0660472	best: 0.0660467 (788)	total: 17m 57s	remaining: 3m 40s
830:	learn: 0.0660118	test: 0.0660472	best: 0.0660467 (788)	total: 17m 58s	remaining: 3m 39s
831:	learn: 0.0660118	test: 0.0660471	best: 0.0660467 (788)	total: 17m 59s	remaining: 3m 37s
832:	learn: 0.0660118	test: 0.0660471	best: 0.0660467 (788)	total: 18m	remaining: 3m 36s
833:	learn: 0.0660116	test: 0.0660472	best: 0.0660467 (788)	total: 18m 1s	remaining: 3m 35s
834:	learn: 0.0660115	test: 0.0660472	best: 0.0660467 (788)	total: 18m 3s	remaining: 3m 34s
835:	learn: 0.0660115	test: 0.0660471	best: 0.0660467 (788)	total: 18m 3s	remaining: 3m 32s
836:	learn: 0.0660113	test: 0.0660472	best: 0.0660467 (788)	total: 18m 5s	remaining: 3m 31s
837:	learn: 0.0660109	test: 0.0660471	best: 0.0660467 (788)	total: 18m 7s	remaining: 3m 30s
838:	learn: 0.0660106	test: 0.0660471	best: 0.0660467 (788)	total: 18m 9s	remaining: 3m 28s
839:	learn: 0.0660106	test: 0.0660471	best: 0.0660467 (788)	total: 18m 10s	remaining: 3m 27s
840:	learn: 0.0660105	test: 0.0660472	best: 0.0660467 (788)	total: 18m 11s	remaining: 3m 26s
841:	learn: 0.0660105	test: 0.0660472	best: 0.0660467 (788)	total: 18m 12s	remaining: 3m 25s
842:	learn: 0.0660105	test: 0.0660472	best: 0.0660467 (788)	total: 18m 13s	remaining: 3m 23s
843:	learn: 0.0660105	test: 0.0660471	best: 0.0660467 (788)	total: 18m 14s	remaining: 3m 22s
844:	learn: 0.0660105	test: 0.0660471	best: 0.0660467 (788)	total: 18m 14s	remaining: 3m 20s
845:	learn: 0.0660104	test: 0.0660471	best: 0.0660467 (788)	total: 18m 15s	remaining: 3m 19s
846:	learn: 0.0660104	test: 0.0660471	best: 0.0660467 (788)	total: 18m 16s	remaining: 3m 18s
847:	learn: 0.0660101	test: 0.0660472	best: 0.0660467 (788)	total: 18m 18s	remaining: 3m 16s
848:	learn: 0.0660098	test: 0.0660471	best: 0.0660467 (788)	total: 18m 20s	remaining: 3m 15s
849:	learn: 0.0660095	test: 0.0660469	best: 0.0660467 (788)	total: 18m 22s	remaining: 3m 14s
850:	learn: 0.0660094	test: 0.0660469	best: 0.0660467 (788)	total: 18m 23s	remaining: 3m 13s
851:	learn: 0.0660091	test: 0.0660472	best: 0.0660467 (788)	total: 18m 25s	remaining: 3m 11s
852:	learn: 0.0660088	test: 0.0660472	best: 0.0660467 (788)	total: 18m 26s	remaining: 3m 10s
853:	learn: 0.0660088	test: 0.0660472	best: 0.0660467 (788)	total: 18m 27s	remaining: 3m 9s
854:	learn: 0.0660088	test: 0.0660472	best: 0.0660467 (788)	total: 18m 28s	remaining: 3m 8s
855:	learn: 0.0660088	test: 0.0660472	best: 0.0660467 (788)	total: 18m 29s	remaining: 3m 6s
856:	learn: 0.0660088	test: 0.0660472	best: 0.0660467 (788)	total: 18m 30s	remaining: 3m 5s
857:	learn: 0.0660088	test: 0.0660472	best: 0.0660467 (788)	total: 18m 31s	remaining: 3m 3s
858:	learn: 0.0660088	test: 0.0660472	best: 0.0660467 (788)	total: 18m 32s	remaining: 3m 2s
859:	learn: 0.0660087	test: 0.0660472	best: 0.0660467 (788)	total: 18m 33s	remaining: 3m 1s
860:	learn: 0.0660086	test: 0.0660473	best: 0.0660467 (788)	total: 18m 34s	remaining: 2m 59s
861:	learn: 0.0660081	test: 0.0660472	best: 0.0660467 (788)	total: 18m 36s	remaining: 2m 58s
862:	learn: 0.0660080	test: 0.0660472	best: 0.0660467 (788)	total: 18m 38s	remaining: 2m 57s
863:	learn: 0.0660079	test: 0.0660472	best: 0.0660467 (788)	total: 18m 40s	remaining: 2m 56s
864:	learn: 0.0660079	test: 0.0660472	best: 0.0660467 (788)	total: 18m 41s	remaining: 2m 54s
865:	learn: 0.0660079	test: 0.0660472	best: 0.0660467 (788)	total: 18m 41s	remaining: 2m 53s
866:	learn: 0.0660077	test: 0.0660473	best: 0.0660467 (788)	total: 18m 42s	remaining: 2m 52s
867:	learn: 0.0660077	test: 0.0660473	best: 0.0660467 (788)	total: 18m 43s	remaining: 2m 50s
868:	learn: 0.0660073	test: 0.0660472	best: 0.0660467 (788)	total: 18m 45s	remaining: 2m 49s
869:	learn: 0.0660070	test: 0.0660471	best: 0.0660467 (788)	total: 18m 47s	remaining: 2m 48s
870:	learn: 0.0660070	test: 0.0660471	best: 0.0660467 (788)	total: 18m 48s	remaining: 2m 47s
871:	learn: 0.0660069	test: 0.0660472	best: 0.0660467 (788)	total: 18m 50s	remaining: 2m 45s
872:	learn: 0.0660067	test: 0.0660473	best: 0.0660467 (788)	total: 18m 51s	remaining: 2m 44s
873:	learn: 0.0660064	test: 0.0660474	best: 0.0660467 (788)	total: 18m 53s	remaining: 2m 43s
874:	learn: 0.0660064	test: 0.0660474	best: 0.0660467 (788)	total: 18m 54s	remaining: 2m 42s
875:	learn: 0.0660063	test: 0.0660474	best: 0.0660467 (788)	total: 18m 55s	remaining: 2m 40s
876:	learn: 0.0660063	test: 0.0660474	best: 0.0660467 (788)	total: 18m 56s	remaining: 2m 39s
877:	learn: 0.0660058	test: 0.0660476	best: 0.0660467 (788)	total: 18m 58s	remaining: 2m 38s
878:	learn: 0.0660058	test: 0.0660475	best: 0.0660467 (788)	total: 18m 59s	remaining: 2m 36s
879:	learn: 0.0660058	test: 0.0660475	best: 0.0660467 (788)	total: 19m	remaining: 2m 35s
880:	learn: 0.0660056	test: 0.0660476	best: 0.0660467 (788)	total: 19m 1s	remaining: 2m 34s
881:	learn: 0.0660056	test: 0.0660476	best: 0.0660467 (788)	total: 19m 2s	remaining: 2m 32s
882:	learn: 0.0660052	test: 0.0660476	best: 0.0660467 (788)	total: 19m 4s	remaining: 2m 31s
883:	learn: 0.0660052	test: 0.0660476	best: 0.0660467 (788)	total: 19m 5s	remaining: 2m 30s
884:	learn: 0.0660049	test: 0.0660476	best: 0.0660467 (788)	total: 19m 7s	remaining: 2m 29s
885:	learn: 0.0660045	test: 0.0660478	best: 0.0660467 (788)	total: 19m 9s	remaining: 2m 27s
886:	learn: 0.0660045	test: 0.0660478	best: 0.0660467 (788)	total: 19m 9s	remaining: 2m 26s
887:	learn: 0.0660043	test: 0.0660480	best: 0.0660467 (788)	total: 19m 11s	remaining: 2m 25s
888:	learn: 0.0660042	test: 0.0660480	best: 0.0660467 (788)	total: 19m 11s	remaining: 2m 23s
889:	learn: 0.0660041	test: 0.0660480	best: 0.0660467 (788)	total: 19m 13s	remaining: 2m 22s
890:	learn: 0.0660041	test: 0.0660480	best: 0.0660467 (788)	total: 19m 14s	remaining: 2m 21s
891:	learn: 0.0660039	test: 0.0660480	best: 0.0660467 (788)	total: 19m 16s	remaining: 2m 20s
892:	learn: 0.0660039	test: 0.0660479	best: 0.0660467 (788)	total: 19m 17s	remaining: 2m 18s
893:	learn: 0.0660036	test: 0.0660477	best: 0.0660467 (788)	total: 19m 19s	remaining: 2m 17s
894:	learn: 0.0660035	test: 0.0660479	best: 0.0660467 (788)	total: 19m 20s	remaining: 2m 16s
895:	learn: 0.0660033	test: 0.0660479	best: 0.0660467 (788)	total: 19m 21s	remaining: 2m 14s
896:	learn: 0.0660032	test: 0.0660478	best: 0.0660467 (788)	total: 19m 23s	remaining: 2m 13s
897:	learn: 0.0660030	test: 0.0660478	best: 0.0660467 (788)	total: 19m 25s	remaining: 2m 12s
898:	learn: 0.0660030	test: 0.0660478	best: 0.0660467 (788)	total: 19m 26s	remaining: 2m 11s
899:	learn: 0.0660030	test: 0.0660478	best: 0.0660467 (788)	total: 19m 26s	remaining: 2m 9s
900:	learn: 0.0660030	test: 0.0660478	best: 0.0660467 (788)	total: 19m 28s	remaining: 2m 8s
901:	learn: 0.0660030	test: 0.0660478	best: 0.0660467 (788)	total: 19m 29s	remaining: 2m 7s
902:	learn: 0.0660030	test: 0.0660478	best: 0.0660467 (788)	total: 19m 30s	remaining: 2m 5s
903:	learn: 0.0660028	test: 0.0660478	best: 0.0660467 (788)	total: 19m 32s	remaining: 2m 4s
904:	learn: 0.0660024	test: 0.0660482	best: 0.0660467 (788)	total: 19m 33s	remaining: 2m 3s
905:	learn: 0.0660024	test: 0.0660481	best: 0.0660467 (788)	total: 19m 34s	remaining: 2m 1s
906:	learn: 0.0660023	test: 0.0660481	best: 0.0660467 (788)	total: 19m 36s	remaining: 2m
907:	learn: 0.0660018	test: 0.0660480	best: 0.0660467 (788)	total: 19m 37s	remaining: 1m 59s
908:	learn: 0.0660017	test: 0.0660480	best: 0.0660467 (788)	total: 19m 39s	remaining: 1m 58s
909:	learn: 0.0660017	test: 0.0660480	best: 0.0660467 (788)	total: 19m 40s	remaining: 1m 56s
910:	learn: 0.0660017	test: 0.0660480	best: 0.0660467 (788)	total: 19m 41s	remaining: 1m 55s
911:	learn: 0.0660015	test: 0.0660481	best: 0.0660467 (788)	total: 19m 43s	remaining: 1m 54s
912:	learn: 0.0660015	test: 0.0660481	best: 0.0660467 (788)	total: 19m 43s	remaining: 1m 52s
913:	learn: 0.0660014	test: 0.0660481	best: 0.0660467 (788)	total: 19m 44s	remaining: 1m 51s
914:	learn: 0.0660011	test: 0.0660481	best: 0.0660467 (788)	total: 19m 46s	remaining: 1m 50s
915:	learn: 0.0660011	test: 0.0660481	best: 0.0660467 (788)	total: 19m 46s	remaining: 1m 48s
916:	learn: 0.0660011	test: 0.0660481	best: 0.0660467 (788)	total: 19m 47s	remaining: 1m 47s
917:	learn: 0.0660009	test: 0.0660481	best: 0.0660467 (788)	total: 19m 49s	remaining: 1m 46s
918:	learn: 0.0660008	test: 0.0660481	best: 0.0660467 (788)	total: 19m 50s	remaining: 1m 44s
919:	learn: 0.0660008	test: 0.0660481	best: 0.0660467 (788)	total: 19m 50s	remaining: 1m 43s
920:	learn: 0.0660008	test: 0.0660481	best: 0.0660467 (788)	total: 19m 52s	remaining: 1m 42s
921:	learn: 0.0660008	test: 0.0660480	best: 0.0660467 (788)	total: 19m 52s	remaining: 1m 40s
922:	learn: 0.0660008	test: 0.0660481	best: 0.0660467 (788)	total: 19m 54s	remaining: 1m 39s
923:	learn: 0.0660008	test: 0.0660481	best: 0.0660467 (788)	total: 19m 54s	remaining: 1m 38s
924:	learn: 0.0660008	test: 0.0660480	best: 0.0660467 (788)	total: 19m 55s	remaining: 1m 36s
925:	learn: 0.0660007	test: 0.0660481	best: 0.0660467 (788)	total: 19m 57s	remaining: 1m 35s
926:	learn: 0.0660007	test: 0.0660480	best: 0.0660467 (788)	total: 19m 58s	remaining: 1m 34s
927:	learn: 0.0660006	test: 0.0660480	best: 0.0660467 (788)	total: 19m 59s	remaining: 1m 33s
928:	learn: 0.0660006	test: 0.0660480	best: 0.0660467 (788)	total: 20m 1s	remaining: 1m 31s
929:	learn: 0.0660005	test: 0.0660481	best: 0.0660467 (788)	total: 20m 2s	remaining: 1m 30s
930:	learn: 0.0660005	test: 0.0660481	best: 0.0660467 (788)	total: 20m 3s	remaining: 1m 29s
931:	learn: 0.0660002	test: 0.0660479	best: 0.0660467 (788)	total: 20m 5s	remaining: 1m 27s
932:	learn: 0.0660000	test: 0.0660480	best: 0.0660467 (788)	total: 20m 7s	remaining: 1m 26s
933:	learn: 0.0660000	test: 0.0660479	best: 0.0660467 (788)	total: 20m 8s	remaining: 1m 25s
934:	learn: 0.0660000	test: 0.0660479	best: 0.0660467 (788)	total: 20m 10s	remaining: 1m 24s
935:	learn: 0.0659999	test: 0.0660479	best: 0.0660467 (788)	total: 20m 11s	remaining: 1m 22s
936:	learn: 0.0659999	test: 0.0660479	best: 0.0660467 (788)	total: 20m 12s	remaining: 1m 21s
937:	learn: 0.0659995	test: 0.0660478	best: 0.0660467 (788)	total: 20m 14s	remaining: 1m 20s
938:	learn: 0.0659992	test: 0.0660477	best: 0.0660467 (788)	total: 20m 15s	remaining: 1m 18s
939:	learn: 0.0659991	test: 0.0660476	best: 0.0660467 (788)	total: 20m 16s	remaining: 1m 17s
940:	learn: 0.0659985	test: 0.0660480	best: 0.0660467 (788)	total: 20m 18s	remaining: 1m 16s
941:	learn: 0.0659985	test: 0.0660480	best: 0.0660467 (788)	total: 20m 19s	remaining: 1m 15s
942:	learn: 0.0659984	test: 0.0660480	best: 0.0660467 (788)	total: 20m 20s	remaining: 1m 13s
943:	learn: 0.0659983	test: 0.0660479	best: 0.0660467 (788)	total: 20m 21s	remaining: 1m 12s
944:	learn: 0.0659980	test: 0.0660481	best: 0.0660467 (788)	total: 20m 22s	remaining: 1m 11s
945:	learn: 0.0659980	test: 0.0660481	best: 0.0660467 (788)	total: 20m 23s	remaining: 1m 9s
946:	learn: 0.0659979	test: 0.0660480	best: 0.0660467 (788)	total: 20m 25s	remaining: 1m 8s
947:	learn: 0.0659979	test: 0.0660480	best: 0.0660467 (788)	total: 20m 25s	remaining: 1m 7s
948:	learn: 0.0659977	test: 0.0660480	best: 0.0660467 (788)	total: 20m 27s	remaining: 1m 5s
949:	learn: 0.0659974	test: 0.0660481	best: 0.0660467 (788)	total: 20m 28s	remaining: 1m 4s
950:	learn: 0.0659974	test: 0.0660481	best: 0.0660467 (788)	total: 20m 29s	remaining: 1m 3s
951:	learn: 0.0659974	test: 0.0660481	best: 0.0660467 (788)	total: 20m 31s	remaining: 1m 2s
952:	learn: 0.0659974	test: 0.0660481	best: 0.0660467 (788)	total: 20m 31s	remaining: 1m
953:	learn: 0.0659973	test: 0.0660481	best: 0.0660467 (788)	total: 20m 33s	remaining: 59.5s
954:	learn: 0.0659971	test: 0.0660480	best: 0.0660467 (788)	total: 20m 34s	remaining: 58.2s
955:	learn: 0.0659969	test: 0.0660480	best: 0.0660467 (788)	total: 20m 36s	remaining: 56.9s
956:	learn: 0.0659969	test: 0.0660480	best: 0.0660467 (788)	total: 20m 37s	remaining: 55.6s
957:	learn: 0.0659967	test: 0.0660479	best: 0.0660467 (788)	total: 20m 39s	remaining: 54.3s
958:	learn: 0.0659967	test: 0.0660479	best: 0.0660467 (788)	total: 20m 39s	remaining: 53s
959:	learn: 0.0659967	test: 0.0660479	best: 0.0660467 (788)	total: 20m 40s	remaining: 51.7s
960:	learn: 0.0659967	test: 0.0660479	best: 0.0660467 (788)	total: 20m 41s	remaining: 50.4s
961:	learn: 0.0659967	test: 0.0660479	best: 0.0660467 (788)	total: 20m 41s	remaining: 49.1s
962:	learn: 0.0659967	test: 0.0660479	best: 0.0660467 (788)	total: 20m 43s	remaining: 47.8s
963:	learn: 0.0659967	test: 0.0660479	best: 0.0660467 (788)	total: 20m 44s	remaining: 46.5s
964:	learn: 0.0659967	test: 0.0660479	best: 0.0660467 (788)	total: 20m 44s	remaining: 45.1s
965:	learn: 0.0659962	test: 0.0660481	best: 0.0660467 (788)	total: 20m 46s	remaining: 43.9s
966:	learn: 0.0659962	test: 0.0660481	best: 0.0660467 (788)	total: 20m 48s	remaining: 42.6s
967:	learn: 0.0659959	test: 0.0660482	best: 0.0660467 (788)	total: 20m 49s	remaining: 41.3s
968:	learn: 0.0659959	test: 0.0660482	best: 0.0660467 (788)	total: 20m 51s	remaining: 40s
969:	learn: 0.0659954	test: 0.0660484	best: 0.0660467 (788)	total: 20m 52s	remaining: 38.8s
970:	learn: 0.0659954	test: 0.0660484	best: 0.0660467 (788)	total: 20m 53s	remaining: 37.4s
971:	learn: 0.0659954	test: 0.0660483	best: 0.0660467 (788)	total: 20m 54s	remaining: 36.1s
972:	learn: 0.0659954	test: 0.0660483	best: 0.0660467 (788)	total: 20m 55s	remaining: 34.8s
973:	learn: 0.0659952	test: 0.0660483	best: 0.0660467 (788)	total: 20m 57s	remaining: 33.6s
974:	learn: 0.0659952	test: 0.0660483	best: 0.0660467 (788)	total: 20m 57s	remaining: 32.3s
975:	learn: 0.0659950	test: 0.0660484	best: 0.0660467 (788)	total: 20m 59s	remaining: 31s
976:	learn: 0.0659948	test: 0.0660484	best: 0.0660467 (788)	total: 21m 1s	remaining: 29.7s
977:	learn: 0.0659944	test: 0.0660486	best: 0.0660467 (788)	total: 21m 2s	remaining: 28.4s
978:	learn: 0.0659943	test: 0.0660486	best: 0.0660467 (788)	total: 21m 4s	remaining: 27.1s
979:	learn: 0.0659943	test: 0.0660486	best: 0.0660467 (788)	total: 21m 5s	remaining: 25.8s
980:	learn: 0.0659941	test: 0.0660486	best: 0.0660467 (788)	total: 21m 7s	remaining: 24.6s
981:	learn: 0.0659941	test: 0.0660486	best: 0.0660467 (788)	total: 21m 8s	remaining: 23.3s
982:	learn: 0.0659941	test: 0.0660486	best: 0.0660467 (788)	total: 21m 9s	remaining: 21.9s
983:	learn: 0.0659940	test: 0.0660486	best: 0.0660467 (788)	total: 21m 10s	remaining: 20.7s
984:	learn: 0.0659940	test: 0.0660487	best: 0.0660467 (788)	total: 21m 12s	remaining: 19.4s
985:	learn: 0.0659937	test: 0.0660489	best: 0.0660467 (788)	total: 21m 13s	remaining: 18.1s
986:	learn: 0.0659936	test: 0.0660489	best: 0.0660467 (788)	total: 21m 15s	remaining: 16.8s
987:	learn: 0.0659932	test: 0.0660491	best: 0.0660467 (788)	total: 21m 17s	remaining: 15.5s
988:	learn: 0.0659932	test: 0.0660491	best: 0.0660467 (788)	total: 21m 17s	remaining: 14.2s
989:	learn: 0.0659928	test: 0.0660491	best: 0.0660467 (788)	total: 21m 19s	remaining: 12.9s
990:	learn: 0.0659927	test: 0.0660490	best: 0.0660467 (788)	total: 21m 20s	remaining: 11.6s
991:	learn: 0.0659924	test: 0.0660491	best: 0.0660467 (788)	total: 21m 21s	remaining: 10.3s
992:	learn: 0.0659924	test: 0.0660491	best: 0.0660467 (788)	total: 21m 23s	remaining: 9.04s
993:	learn: 0.0659923	test: 0.0660491	best: 0.0660467 (788)	total: 21m 24s	remaining: 7.75s
994:	learn: 0.0659921	test: 0.0660490	best: 0.0660467 (788)	total: 21m 25s	remaining: 6.46s
995:	learn: 0.0659918	test: 0.0660491	best: 0.0660467 (788)	total: 21m 27s	remaining: 5.17s
996:	learn: 0.0659916	test: 0.0660488	best: 0.0660467 (788)	total: 21m 29s	remaining: 3.88s
997:	learn: 0.0659915	test: 0.0660488	best: 0.0660467 (788)	total: 21m 30s	remaining: 2.59s
998:	learn: 0.0659915	test: 0.0660488	best: 0.0660467 (788)	total: 21m 31s	remaining: 1.29s
999:	learn: 0.0659914	test: 0.0660488	best: 0.0660467 (788)	total: 21m 33s	remaining: 0us

bestTest = 0.06604674677
bestIteration = 788

Out[212]:
<catboost.core.CatBoostClassifier at 0x19f8a857cc0>

In [217]:
prediction_proba = model.predict_proba(test)

In [219]:
prediction_proba[:,1]


Out[219]:
array([ 0.01567,  0.01569,  0.0155 , ...,  0.02772,  0.02941,  0.02941])

In [204]:
def make_submission(probs):
    sample = pd.read_csv(f'{PATH}//sample_submission.csv')
    submit = sample.copy()
    submit['is_click'] = probs
    return submit

In [221]:
submit = make_submission(prediction_proba[:,1])

In [222]:
submit.head(2)


Out[222]:
id is_click
0 63_122715 0.015673
1 56_76206 0.015691

In [223]:
submit.to_csv(PATH + '//logistic_reg_sub2.csv', index=False)

In [201]:
from  sklearn.metrics  import  mean_squared_error

from  sklearn.preprocessing  import  StandardScaler 
from  sklearn.model_selection  import  GridSearchCV
from  sklearn.linear_model  import   LogisticRegression 
from  sklearn.linear_model  import   LinearRegression 
from  sklearn.neighbors  import   KNeighborsRegressor 
from  sklearn.ensemble  import   RandomForestRegressor 
from  sklearn.ensemble  import   GradientBoostingRegressor 
from  sklearn.ensemble  import   AdaBoostRegressor 
from  sklearn.svm  import  LinearSVR

from  sklearn.learning_curve  import  learning_curve

from  scipy  import  stats

In [203]:
X_train, X_validation, y_train, y_validation = train_test_split(df_raw, y_target, train_size=0.8, random_state=17)


C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_split.py:2026: FutureWarning: From version 0.21, test_size will always complement train_size unless both are specified.
  FutureWarning)

In [ ]:
# We teach the basic random forest for the selection of characteristics 
rfc_base = RandomForestRegressor ( n_estimators = 500 , random_state = 42,n_jobs=-1 ) 
rfc_base . fit ( X_train , y_train )

In [ ]:
# Display the significance of features 
features  =  pd . DataFrame ( rfc_base.feature_importances_ ,  index = X_train . columns , 
                        columns = [ 'Importance' ]) . sort_values ([ 'Importance' ],  ascending = False ) 
features

In [ ]:
# Let's 
start choosing a model # List of regressors regressors 
= [ LinearRegression (), GradientBoostingRegressor ( random_state = 17 ), RandomForestRegressor ( random_state = 17 ), LinearSVR ( random_state = 17 )]

regressor_name = [ 'LinearRegression' , 'GradientBoostingRegressor' , 'RandomForestRegressor' , 'LinearSVR' ]

In [ ]:
# Parameters to the regressors 
scores  =  [] 
fits  =  [] 
linear_params  =  { 'normalize' :  ( True ,  False )} 
gbr_params  =  { 'n_estimators' :  [ 100 ,  300 ,  500 ], 
              'learning_rate' :( 0.1 ,  0.5 ,  1 ), 
              'max_depth' :  list ( range ( 3 ,  10 ,  2 )),  
              'min_samples_leaf':  list ( range ( 10 ,  31 ,  10 ))} 
forest_params  =  { 'n_estimators' :  [ 100 ,  300 ,  500 ],  
                 'max_depth' :  list ( range ( 3 ,  10 ,  2 )),  
                 'min_samples_leaf' :  list ( range ( 10 ,  31 ,  10 ))}

svm_params  =  { 'loss'  :  ( 'epsilon_insensitive' ,  'squared_epsilon_insensitive' ),  'C' :  ( . 5 ,  1 ,  2 )} 
params  =  [ linear_params ,  gbr_params ,  forest_params ,  svm_params ]

In [ ]:
# We search the regressors parameters in search of the best (on 5 folds) 
np . random . seed ( 42 ) 
for  i ,  each_regressor  in  enumerate ( regressors ): 
    reg  =  each_regressor 
    reg_params  =  params [ i ] 
    grid  =  GridSearchCV ( reg ,  reg_params ,  
                        cv = 5 , 
                        scoring = 'neg_mean_squared_error' , 
                        n_jobs = -1 )
    grid . fit ( X_train ,  y_train ) 
    fits . append ( grid . best_params_ ) 
    reg_best_score  =  grid . best_score_ 
    scores . append ( reg_best_score ) 
    print ( regressor_name [ i ],  - reg_best_score ,  " \ n " ,  grid . best_params_ ,  " \ n " )

In [ ]:
# In-depth selection of hyperparameters for a random forest 
np . random . seed ( 42 ) 
forest_params_deep  =  { 'n_estimators' :  [ 100 , 150 , 200 , 300 , 500 ],  #n_estimators - number of trees in the random forest 
                 'max_depth' :  list ( range ( 3 ,  13 ,  2 )),  #max_depth - maximum depth of the tree 
                 'min_samples_leaf' :  list ( range( 5 ,  30 ,  5 ))} #min_samples_leaf - the minimum number of objects in the tree sheet. 
rfr = RandomForestRegressor ( random_state = 42 ) 
grid_rfr  =  GridSearchCV ( rfr ,  forest_params_deep ,  
                        cv = 5 , 
                        scoring = 'neg_mean_squared_error' , 
                        n_jobs = -1 )

In [ ]:
grid_rfr . fit ( X_train ,  y_train )

In [ ]:
# The result is even better! 
print ( - grid_rfr . best_score_ , ' \ n ' , grid_rfr . best_params_ )

25/03/18


In [6]:



Out[6]:
0
id 42_14051
user_id 14051
campaign_id 42
is_open 0
is_click 0
send_Year 2017
send_Month 1
send_Week 2
send_Day 9
send_Dayofweek 0
send_Dayofyear 9
send_Is_month_end False
send_Is_month_start False
send_Is_quarter_end False
send_Is_quarter_start False
send_Is_year_end False
send_Is_year_start False
total_links 88
no_of_internal_links 79
no_of_images 13
no_of_sections 4
len_email_body 52
diversity_email_body 0.0419682
diversity_subject 0.386364
body_per_sec 13
diversity_email_url 0.457143
img_per_sec 3.25
other_links 9
av_links_percent 0.897727
links_per_sec 22
... ...
code_email_url_7vtb2vb5p4c 0
code_email_url_7vv5g7b5p4c 0
code_email_url_7vzmmvb5p4c 0
code_email_url_7w2sevb5p4c 0
code_email_url_7w3uc7b5p4c 0
code_email_url_7w43tjb5p4c 0
code_email_url_7w5y6vb5p4c 0
code_email_url_7w6qmvb5p4c 0
code_email_url_7w7047b5p4c 0
code_email_url_7wghg7b5p4c 0
code_email_url_7wh9w7b5p4c 0
code_email_url_7whsuvb5p4c 0
code_email_url_7wjn87b5p4c 0
code_email_url_7wjwpjb5p4c 0
code_email_url_7wkfo7b5p4c 0
code_email_url_7wnbyvb5p4c 0
code_email_url_7wo4evb5p4c 0
code_email_url_7wowuvb5p4c 0
code_email_url_7wppavb5p4c 0
code_email_url_7wqhqvb5p4c 0
code_email_url_7wra6vb5p4c 0
code_email_url_7wrjo7b5p4c 0
code_email_url_7ww0uvb5p4c 0
code_email_url_7wx2s7b5p4c 0
code_email_url_7wxlqvb5p4c 0
code_email_url_7wxv87b5p4c 0
code_email_url_7wz6mvb5p4c 0
code_email_url_7wzpljb5p4c 0
code_email_url_7x08k7b5p4c 0
code_email_url_o7ohwml8lxh 0

89 rows × 1 columns


In [ ]: