In [1]:

    

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import os
%matplotlib inline


    

In [2]:

    

from xgboost import XGBClassifier
from catboost import CatBoostClassifier


    

In [3]:

    

from datetime import datetime


    

In [4]:

    

numeric_prefix = "train_numeric_"
categoric_prefix = "train_categorical_onehot_"
item_date_prefix = "item_station_date_"


    

In [5]:

    

import glob
def count_forests(dirname):
    fnames = glob.glob1(dirname, numeric_prefix + "*")
    return len(fnames)


    

In [ ]:

    




    

In [6]:

    

def file_list_generator(dirname):
    forest_count = count_forests(dirname)
    for i in range(forest_count):
        suffix = "{0:04d}".format(i)
        yield os.path.join(dirname, numeric_prefix + suffix), \
              os.path.join(dirname, categoric_prefix + suffix), \
              os.path.join(dirname, item_date_prefix + suffix)


    

In [7]:

    

def read_columns_from_file(fname):
    columns = pd.read_csv(fname, nrows=2).columns
    return columns


    

In [8]:

    

numeric_columns = read_columns_from_file("../../../input/train_numeric.csv")
categoric_columns = read_columns_from_file("../../../input/train_categorical_onehot.csv")
item_date_columns = read_columns_from_file("../../../input/item_station_date.csv")


    

In [ ]:

    




    

In [9]:

    

def load_data_files(fn, fc=None, fid=None):
    df = pd.read_csv(fn, names=numeric_columns, index_col="Id", dtype=np.float32)

    if fc != None:
        temp_df = pd.read_csv(fc, names=categoric_columns, index_col='Id', dtype=np.int32)
        df = df.join(temp_df, how='inner')
        del temp_df

    if fid != None:
        temp_df = pd.read_csv(fid, names=item_date_columns, index_col='Id', dtype=np.float32)
        df = df.join(temp_df, how='inner')
        del temp_df
    
    return df


    

In [10]:

    

file_list = list(file_list_generator("bs4600"))

forest_list = []

for idx, (fn, fc, fid) in enumerate(file_list):
    t0 = datetime.now()
    print "Forest #{0}".format(idx)

    df = load_data_files(fn, fid=fid)
    print "Loaded in", datetime.now() - t0, 

    y = df['Response'].values
    del df['Response']
    X = df.values

    xgb = CatBoostClassifier()
    xgb.fit(X, y)
    forest_list.append(xgb)
    print "Done in", datetime.now() - t0


    

    




Forest #0
Loaded in 0:00:00.720000 Done in 0:01:22.623000
Forest #1
Loaded in 0:00:00.658000 Done in 0:01:23.876000
Forest #2
Loaded in 0:00:00.654000 Done in 0:01:25.284000
Forest #3
Loaded in 0:00:00.659000 Done in 0:01:22.128000
Forest #4
Loaded in 0:00:00.716000 Done in 0:01:23.650000
Forest #5
Loaded in 0:00:00.650000 Done in 0:01:24.648000
Forest #6
Loaded in 0:00:00.709000 Done in 0:01:26.652000
Forest #7
Loaded in 0:00:00.760000 Done in 0:01:24.787000
Forest #8
Loaded in 0:00:00.686000 Done in 0:01:23.763000
Forest #9
Loaded in 0:00:00.671000 Done in 0:01:21.894000
Forest #10
Loaded in 0:00:00.798000 Done in 0:01:22.950000
Forest #11
Loaded in 0:00:00.805000 Done in 0:01:22.713000
Forest #12
Loaded in 0:00:00.862000 Done in 0:01:26.067000
Forest #13
Loaded in 0:00:00.845000 Done in 0:01:26.118000
Forest #14
Loaded in 0:00:00.805000 Done in 0:01:23.437000
Forest #15
Loaded in 0:00:00.795000 Done in 0:01:24.126000
Forest #16
Loaded in 0:00:00.858000 Done in 0:01:22.409000
Forest #17
Loaded in 0:00:00.790000 Done in 0:01:23.857000
Forest #18
Loaded in 0:00:00.847000 Done in 0:01:26.784000
Forest #19
Loaded in 0:00:00.940000 Done in 0:01:28.039000
Forest #20
Loaded in 0:00:00.744000 Done in 0:01:26.946000
Forest #21
Loaded in 0:00:00.788000 Done in 0:01:27.530000
Forest #22
Loaded in 0:00:00.753000 Done in 0:01:26.642000
Forest #23
Loaded in 0:00:00.864000 Done in 0:01:26.727000
Forest #24
Loaded in 0:00:00.789000 Done in 0:01:25.381000
Forest #25
Loaded in 0:00:00.814000 Done in 0:01:24.783000
Forest #26
Loaded in 0:00:00.776000 Done in 0:01:25.505000
Forest #27
Loaded in 0:00:00.822000 Done in 0:01:25.598000
Forest #28
Loaded in 0:00:00.802000 Done in 0:01:23.731000
Forest #29
Loaded in 0:00:00.790000 Done in 0:01:25.042000
Forest #30
Loaded in 0:00:00.794000 Done in 0:01:23.416000
Forest #31
Loaded in 0:00:00.816000 Done in 0:01:23.195000
Forest #32
Loaded in 0:00:00.785000 Done in 0:01:22.575000
Forest #33
Loaded in 0:00:00.789000 Done in 0:01:24.234000
Forest #34
Loaded in 0:00:00.841000 Done in 0:01:24.602000
Forest #35
Loaded in 0:00:00.852000 Done in 0:01:24.737000
Forest #36
Loaded in 0:00:00.811000 Done in 0:01:21.866000
Forest #37
Loaded in 0:00:00.769000 Done in 0:01:22.094000
Forest #38
Loaded in 0:00:00.781000 Done in 0:01:21.172000
Forest #39
Loaded in 0:00:00.821000 Done in 0:01:22.845000
Forest #40
Loaded in 0:00:00.780000 Done in 0:01:21.824000
Forest #41
Loaded in 0:00:00.780000 Done in 0:01:20.550000
Forest #42
Loaded in 0:00:00.790000 Done in 0:01:23.552000
Forest #43
Loaded in 0:00:00.800000 Done in 0:01:22.378000
Forest #44
Loaded in 0:00:00.788000 Done in 0:01:23.566000
Forest #45
Loaded in 0:00:00.766000 Done in 0:01:21.360000
Forest #46
Loaded in 0:00:00.759000 Done in 0:01:24.400000
Forest #47
Loaded in 0:00:00.802000 Done in 0:01:24.944000
Forest #48
Loaded in 0:00:00.813000 Done in 0:01:23.143000
Forest #49
Loaded in 0:00:00.779000 Done in 0:01:23.200000
Forest #50
Loaded in 0:00:00.778000 Done in 0:01:23.409000
Forest #51
Loaded in 0:00:00.778000 Done in 0:01:21.438000
Forest #52
Loaded in 0:00:00.765000 Done in 0:01:22.073000
Forest #53
Loaded in 0:00:00.770000 Done in 0:01:23.962000
Forest #54
Loaded in 0:00:00.783000 Done in 0:01:21.526000
Forest #55
Loaded in 0:00:00.774000 Done in 0:01:25.442000
Forest #56
Loaded in 0:00:00.778000 Done in 0:01:21.452000
Forest #57
Loaded in 0:00:00.771000 Done in 0:01:23.099000
Forest #58
Loaded in 0:00:00.758000 Done in 0:01:24.118000
Forest #59
Loaded in 0:00:00.774000 Done in 0:01:22.159000
Forest #60
Loaded in 0:00:00.759000 Done in 0:01:24.243000
Forest #61
Loaded in 0:00:00.796000 Done in 0:01:22.793000
Forest #62
Loaded in 0:00:00.751000 Done in 0:01:23.476000
Forest #63
Loaded in 0:00:00.783000 Done in 0:01:20.885000
Forest #64
Loaded in 0:00:00.751000 Done in 0:01:21.327000
Forest #65
Loaded in 0:00:00.783000 Done in 0:01:22.726000
Forest #66
Loaded in 0:00:00.783000 Done in 0:01:23.502000
Forest #67
Loaded in 0:00:00.789000 Done in 0:01:23.699000
Forest #68
Loaded in 0:00:00.785000 Done in 0:01:23.950000
Forest #69
Loaded in 0:00:00.758000 Done in 0:01:22.549000
Forest #70
Loaded in 0:00:00.753000 Done in 0:01:22.598000
Forest #71
Loaded in 0:00:00.793000 Done in 0:01:23.429000
Forest #72
Loaded in 0:00:00.770000 Done in 0:01:21.800000
Forest #73
Loaded in 0:00:00.768000 Done in 0:01:23.376000
Forest #74
Loaded in 0:00:00.772000 Done in 0:01:20.856000
Forest #75
Loaded in 0:00:00.775000 Done in 0:01:20.845000
Forest #76
Loaded in 0:00:00.775000 Done in 0:01:21.269000
Forest #77
Loaded in 0:00:00.779000 Done in 0:01:20.958000
Forest #78
Loaded in 0:00:00.747000 Done in 0:01:22.760000
Forest #79
Loaded in 0:00:00.781000 Done in 0:01:22.143000
Forest #80
Loaded in 0:00:00.789000 Done in 0:01:21.617000
Forest #81
Loaded in 0:00:00.772000 Done in 0:01:21.868000
Forest #82
Loaded in 0:00:00.746000 Done in 0:01:23.576000
Forest #83
Loaded in 0:00:00.796000 Done in 0:01:20.911000
Forest #84
Loaded in 0:00:00.765000 Done in 0:01:21.551000
Forest #85
Loaded in 0:00:00.745000 Done in 0:01:22.391000
Forest #86
Loaded in 0:00:00.768000 Done in 0:01:23.169000
Forest #87
Loaded in 0:00:00.798000 Done in 0:01:22.110000
Forest #88
Loaded in 0:00:00.775000 Done in 0:01:26.061000
Forest #89
Loaded in 0:00:00.801000 Done in 0:01:29.128000
Forest #90
Loaded in 0:00:00.865000 Done in 0:01:27.552000
Forest #91
Loaded in 0:00:00.867000 Done in 0:01:29.280000
Forest #92
Loaded in 0:00:00.871000 Done in 0:01:27.674000
Forest #93
Loaded in 0:00:00.891000 Done in 0:01:29.493000
Forest #94
Loaded in 0:00:00.887000 Done in 0:01:27.699000
Forest #95
Loaded in 0:00:00.816000 Done in 0:01:23.413000
Forest #96
Loaded in 0:00:00.780000 Done in 0:01:24.228000
Forest #97
Loaded in 0:00:00.776000 Done in 0:01:24.789000
Forest #98
Loaded in 0:00:00.796000 Done in 0:01:24.460000
Forest #99
Loaded in 0:00:00.806000 Done in 0:01:27.185000
Forest #100
Loaded in 0:00:00.898000 Done in 0:01:25.661000
Forest #101
Loaded in 0:00:00.792000 Done in 0:01:30.640000
Forest #102
Loaded in 0:00:00.855000 Done in 0:01:25.016000
Forest #103
Loaded in 0:00:00.785000 Done in 0:01:22.012000
Forest #104
Loaded in 0:00:00.750000 Done in 0:01:24.202000
Forest #105
Loaded in 0:00:00.737000 Done in 0:01:25.172000
Forest #106
Loaded in 0:00:00.777000 Done in 0:01:28.754000
Forest #107
Loaded in 0:00:00.807000 Done in 0:01:26.771000
Forest #108
Loaded in 0:00:00.751000 Done in 0:01:27.073000
Forest #109
Loaded in 0:00:00.746000 Done in 0:01:28.305000
Forest #110
Loaded in 0:00:00.733000 Done in 0:01:26.361000
Forest #111
Loaded in 0:00:00.814000 Done in 0:01:28.376000
Forest #112
Loaded in 0:00:00.759000 Done in 0:01:28.050000
Forest #113
Loaded in 0:00:00.733000 Done in 0:01:26.971000
Forest #114
Loaded in 0:00:00.904000 Done in 0:01:25.522000
Forest #115
Loaded in 0:00:00.841000 Done in 0:01:29.054000
Forest #116
Loaded in 0:00:00.785000 Done in 0:01:27.209000
Forest #117
Loaded in 0:00:00.760000 Done in 0:01:28.732000
Forest #118
Loaded in 0:00:00.756000 Done in 0:01:29.667000
Forest #119
Loaded in 0:00:00.771000 Done in 0:01:28.385000
Forest #120
Loaded in 0:00:00.778000 Done in 0:01:30.181000
Forest #121
Loaded in 0:00:00.851000 Done in 0:01:26.985000
Forest #122
Loaded in 0:00:00.780000 Done in 0:01:26.110000
Forest #123
Loaded in 0:00:00.760000 Done in 0:01:26.171000
Forest #124
Loaded in 0:00:00.716000 Done in 0:01:28.179000
Forest #125
Loaded in 0:00:00.802000 Done in 0:01:25.289000
Forest #126
Loaded in 0:00:00.768000 Done in 0:01:25.185000
Forest #127
Loaded in 0:00:00.735000 Done in 0:01:23.896000
Forest #128
Loaded in 0:00:00.762000 Done in 0:01:23.175000
Forest #129
Loaded in 0:00:00.733000 Done in 0:01:24.205000
Forest #130
Loaded in 0:00:00.763000 Done in 0:01:23.905000
Forest #131
Loaded in 0:00:00.774000 Done in 0:01:24.547000
Forest #132
Loaded in 0:00:00.739000 Done in 0:01:24.477000
Forest #133
Loaded in 0:00:00.732000 Done in 0:01:23.537000
Forest #134
Loaded in 0:00:00.810000 Done in 0:01:23.736000
Forest #135
Loaded in 0:00:00.836000 Done in 0:01:23.889000
Forest #136
Loaded in 0:00:00.770000 Done in 0:01:22.536000
Forest #137
Loaded in 0:00:00.698000 Done in 0:01:23.643000
Forest #138
Loaded in 0:00:00.754000 Done in 0:01:23.007000
Forest #139
Loaded in 0:00:00.781000 Done in 0:01:26.185000
Forest #140
Loaded in 0:00:00.754000 Done in 0:01:22.836000
Forest #141
Loaded in 0:00:00.773000 Done in 0:01:23.852000
Forest #142
Loaded in 0:00:00.855000 Done in 0:01:24.643000
Forest #143
Loaded in 0:00:00.799000 Done in 0:01:23.955000
Forest #144
Loaded in 0:00:00.725000 Done in 0:01:23.581000
Forest #145
Loaded in 0:00:00.769000 Done in 0:01:23.224000
Forest #146
Loaded in 0:00:00.751000 Done in 0:01:24.292000
Forest #147
Loaded in 0:00:00.756000 Done in 0:01:24.198000
Forest #148
Loaded in 0:00:00.737000 Done in 0:01:24.138000
Forest #149
Loaded in 0:00:00.734000 Done in 0:01:23.936000
Forest #150
Loaded in 0:00:00.701000 Done in 0:01:24.754000
Forest #151
Loaded in 0:00:00.750000 Done in 0:01:21.870000
Forest #152
Loaded in 0:00:00.732000 Done in 0:01:24.100000
Forest #153
Loaded in 0:00:00.734000 Done in 0:01:23.070000
Forest #154
Loaded in 0:00:00.732000 Done in 0:01:24.833000
Forest #155
Loaded in 0:00:00.810000 Done in 0:01:24.418000
Forest #156
Loaded in 0:00:00.846000 Done in 0:01:30.742000
Forest #157
Loaded in 0:00:00.827000 Done in 0:01:28.659000
Forest #158
Loaded in 0:00:00.852000 Done in 0:01:31.568000
Forest #159
Loaded in 0:00:00.879000 Done in 0:01:28.863000
Forest #160
Loaded in 0:00:00.827000 Done in 0:01:28.977000
Forest #161
Loaded in 0:00:00.841000 Done in 0:01:32.708000
Forest #162
Loaded in 0:00:00.828000 Done in 0:01:27.151000
Forest #163
Loaded in 0:00:00.740000 Done in 0:01:30.169000
Forest #164
Loaded in 0:00:00.807000 Done in 0:01:28.667000
Forest #165
Loaded in 0:00:00.787000 Done in 0:01:32.767000
Forest #166
Loaded in 0:00:00.807000 Done in 0:01:27.434000
Forest #167
Loaded in 0:00:00.798000 Done in 0:01:32.551000
Forest #168
Loaded in 0:00:00.880000 Done in 0:01:35.896000
Forest #169
Loaded in 0:00:00.891000 Done in 0:01:29.097000
Forest #170
Loaded in 0:00:00.714000 Done in 0:01:25.486000

In [11]:

    

numeric_test_df = pd.read_csv("../../../input/train_numeric_test", names=numeric_columns, index_col="Id", dtype=np.float32)


    

In [12]:

    

item_station_date_df = pd.read_csv("../../../input/item_station_date_test", names=item_date_columns, index_col="Id", dtype=np.float32)


    

In [13]:

    

test_df =  numeric_test_df.join(item_station_date_df, how='inner')


    

In [14]:

    

test_df.shape


    

    
Out[14]:





(394582, 1039)

In [15]:

    

y = test_df['Response'].values
del test_df['Response']
X = test_df.values


    

In [16]:

    

del test_df


    

In [17]:

    

preds = np.zeros(shape=(X.shape[0], 2*len(forest_list)))
preds.shape


    

    
Out[17]:





(394582L, 342L)

In [18]:

    

%%time
for idx, forest in enumerate(forest_list):
    t0 = datetime.now()
    print "Forest #{0}".format(idx)
    pred = forest.predict_proba(X)
    preds[:, 2*idx:2*(idx+1)] = pred
#     pred = forest.predict(X)
#     preds[:, idx] = pred
    print "Predict in", datetime.now() - t0


    

    




Forest #0
Predict in 0:00:38.830000
Forest #1
Predict in 0:00:37.109000
Forest #2
Predict in 0:00:37.423000
Forest #3
Predict in 0:00:37.941000
Forest #4
Predict in 0:00:37.762000
Forest #5
Predict in 0:00:37.880000
Forest #6
Predict in 0:00:38.791000
Forest #7
Predict in 0:00:38.022000
Forest #8
Predict in 0:00:37.351000
Forest #9
Predict in 0:00:37.223000
Forest #10
Predict in 0:00:37.402000
Forest #11
Predict in 0:00:38.240000
Forest #12
Predict in 0:00:42.878000
Forest #13
Predict in 0:00:47.994000
Forest #14
Predict in 0:00:46.288000
Forest #15
Predict in 0:00:43.400000
Forest #16
Predict in 0:00:43.259000
Forest #17
Predict in 0:00:43.217000
Forest #18
Predict in 0:00:43.119000
Forest #19
Predict in 0:00:43.210000
Forest #20
Predict in 0:00:45.419000
Forest #21
Predict in 0:00:42.183000
Forest #22
Predict in 0:00:40.473000
Forest #23
Predict in 0:00:39.164000
Forest #24
Predict in 0:00:39.817000
Forest #25
Predict in 0:00:40.293000
Forest #26
Predict in 0:00:39.177000
Forest #27
Predict in 0:00:39.717000
Forest #28
Predict in 0:00:41.805000
Forest #29
Predict in 0:00:42.834000
Forest #30
Predict in 0:00:42.625000
Forest #31
Predict in 0:00:42.357000
Forest #32
Predict in 0:00:42.903000
Forest #33
Predict in 0:00:41.229000
Forest #34
Predict in 0:00:43.235000
Forest #35
Predict in 0:00:42.250000
Forest #36
Predict in 0:00:39.790000
Forest #37
Predict in 0:00:41.293000
Forest #38
Predict in 0:00:42.011000
Forest #39
Predict in 0:00:43.374000
Forest #40
Predict in 0:00:41.226000
Forest #41
Predict in 0:00:41.024000
Forest #42
Predict in 0:00:42.287000
Forest #43
Predict in 0:00:41.406000
Forest #44
Predict in 0:00:41.291000
Forest #45
Predict in 0:00:41.673000
Forest #46
Predict in 0:00:42.376000
Forest #47
Predict in 0:00:41.534000
Forest #48
Predict in 0:00:40.399000
Forest #49
Predict in 0:00:39.964000
Forest #50
Predict in 0:00:40.795000
Forest #51
Predict in 0:00:41.197000
Forest #52
Predict in 0:00:41.025000
Forest #53
Predict in 0:00:39.645000
Forest #54
Predict in 0:00:40.418000
Forest #55
Predict in 0:00:41.988000
Forest #56
Predict in 0:00:39.732000
Forest #57
Predict in 0:00:40.597000
Forest #58
Predict in 0:00:39.787000
Forest #59
Predict in 0:00:42.921000
Forest #60
Predict in 0:00:41.868000
Forest #61
Predict in 0:00:43.332000
Forest #62
Predict in 0:00:42.782000
Forest #63
Predict in 0:00:44.416000
Forest #64
Predict in 0:00:45.588000
Forest #65
Predict in 0:00:46.039000
Forest #66
Predict in 0:00:50.139000
Forest #67
Predict in 0:00:44.098000
Forest #68
Predict in 0:00:45.303000
Forest #69
Predict in 0:00:42.292000
Forest #70
Predict in 0:00:43.339000
Forest #71
Predict in 0:00:52.274000
Forest #72
Predict in 0:00:46.099000
Forest #73
Predict in 0:00:46.717000
Forest #74
Predict in 0:00:46.730000
Forest #75
Predict in 0:00:48.443000
Forest #76
Predict in 0:00:45.304000
Forest #77
Predict in 0:00:48.029000
Forest #78
Predict in 0:00:48.389000
Forest #79
Predict in 0:00:47.394000
Forest #80
Predict in 0:00:47.568000
Forest #81
Predict in 0:00:47.998000
Forest #82
Predict in 0:00:47.833000
Forest #83
Predict in 0:00:48.090000
Forest #84
Predict in 0:00:46.649000
Forest #85
Predict in 0:00:46.989000
Forest #86
Predict in 0:00:47.646000
Forest #87
Predict in 0:00:45.095000
Forest #88
Predict in 0:00:49.229000
Forest #89
Predict in 0:00:45.490000
Forest #90
Predict in 0:00:48.055000
Forest #91
Predict in 0:00:41.486000
Forest #92
Predict in 0:00:41.644000
Forest #93
Predict in 0:00:40.581000
Forest #94
Predict in 0:00:41.886000
Forest #95
Predict in 0:00:41.786000
Forest #96
Predict in 0:00:41.822000
Forest #97
Predict in 0:00:40.382000
Forest #98
Predict in 0:00:41.514000
Forest #99
Predict in 0:00:41.592000
Forest #100
Predict in 0:00:40.114000
Forest #101
Predict in 0:00:40.850000
Forest #102
Predict in 0:00:41.377000
Forest #103
Predict in 0:00:38.939000
Forest #104
Predict in 0:00:40.412000
Forest #105
Predict in 0:00:40.582000
Forest #106
Predict in 0:00:40.588000
Forest #107
Predict in 0:00:40.532000
Forest #108
Predict in 0:00:40.471000
Forest #109
Predict in 0:00:43.774000
Forest #110
Predict in 0:00:41.503000
Forest #111
Predict in 0:00:42.288000
Forest #112
Predict in 0:00:41.071000
Forest #113
Predict in 0:00:42.106000
Forest #114
Predict in 0:00:39.670000
Forest #115
Predict in 0:00:38.653000
Forest #116
Predict in 0:00:41.947000
Forest #117
Predict in 0:00:43.258000
Forest #118
Predict in 0:00:42.238000
Forest #119
Predict in 0:00:42.906000
Forest #120
Predict in 0:00:43.121000
Forest #121
Predict in 0:00:41.564000
Forest #122
Predict in 0:00:40.115000
Forest #123
Predict in 0:00:40.508000
Forest #124
Predict in 0:00:41.672000
Forest #125
Predict in 0:00:41.322000
Forest #126
Predict in 0:00:42.159000
Forest #127
Predict in 0:00:39.688000
Forest #128
Predict in 0:00:38.323000
Forest #129
Predict in 0:00:44.033000
Forest #130
Predict in 0:00:41.446000
Forest #131
Predict in 0:00:41.871000
Forest #132
Predict in 0:00:38.943000
Forest #133
Predict in 0:00:42.627000
Forest #134
Predict in 0:00:37.877000
Forest #135
Predict in 0:00:37.927000
Forest #136
Predict in 0:00:37.752000
Forest #137
Predict in 0:00:38.613000
Forest #138
Predict in 0:00:39.841000
Forest #139
Predict in 0:00:42.458000
Forest #140
Predict in 0:00:40.568000
Forest #141
Predict in 0:00:40.932000
Forest #142
Predict in 0:00:40.976000
Forest #143
Predict in 0:00:39.017000
Forest #144
Predict in 0:00:38.943000
Forest #145
Predict in 0:00:43.914000
Forest #146
Predict in 0:00:43.588000
Forest #147
Predict in 0:00:43.237000
Forest #148
Predict in 0:00:44.350000
Forest #149
Predict in 0:00:43.062000
Forest #150
Predict in 0:00:43.393000
Forest #151
Predict in 0:00:43.299000
Forest #152
Predict in 0:00:43.470000
Forest #153
Predict in 0:00:42.230000
Forest #154
Predict in 0:00:43.429000
Forest #155
Predict in 0:00:43.927000
Forest #156
Predict in 0:00:43.192000
Forest #157
Predict in 0:00:42.847000
Forest #158
Predict in 0:00:42.925000
Forest #159
Predict in 0:00:43.174000
Forest #160
Predict in 0:00:43.349000
Forest #161
Predict in 0:00:42.903000
Forest #162
Predict in 0:00:43.113000
Forest #163
Predict in 0:00:43.372000
Forest #164
Predict in 0:00:43.266000
Forest #165
Predict in 0:00:43.552000
Forest #166
Predict in 0:00:43.557000
Forest #167
Predict in 0:00:44.181000
Forest #168
Predict in 0:00:43.357000
Forest #169
Predict in 0:00:42.785000
Forest #170
Predict in 0:00:41.314000
Wall time: 2h 32s

In [19]:

    

np.save("n+d_preds_predict_proba.npy", preds)


    

In [20]:

    

np.save("y_true.npy", y)


    

In [ ]: