notebook.community

Edit and run

Facies Classification Solution By Team_BGC

Cheolkyun Jeong and Ping Zhang From Team_BGC

Import Header





In [33]:



    


##### import basic function
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
##### import stuff from scikit learn
from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
from sklearn.metrics import confusion_matrix, make_scorer, f1_score, accuracy_score, recall_score, precision_score

1. Data Prepocessing

1) Filtered data preparation

After the initial data validation, we figure out the NM_M input is a key differentiator to group non-marine stones (sandstone, c_siltstone, and f_siltstone) and marine stones (marine_silt_shale, mudstone, wakestone, dolomite, packstone, and bafflestone) in the current field. Our team decides to use this classifier aggressively and prepare a filtered dataset which cleans up the outliers.





In [34]:



    


# Input file paths
facies_vector_path = 'facies_vectors.csv'
train_path = 'training_data.csv'
test_path = 'validation_data_nofacies.csv'
# Read training data to dataframe
#training_data = pd.read_csv(train_path)

Using Full data to train





In [35]:



    


# 1=sandstone  2=c_siltstone   3=f_siltstone # 4=marine_silt_shale 
#5=mudstone 6=wackestone 7=dolomite 8=packstone 9=bafflestone
facies_colors = ['#F4D03F', '#F5B041', '#DC7633','#A569BD',
       '#000000', '#000080', '#2E86C1', '#AED6F1', '#196F3D']
feature_names = ['GR', 'ILD_log10', 'DeltaPHI', 'PHIND', 'PE', 'NM_M', 'RELPOS']

facies_labels = ['SS', 'CSiS', 'FSiS', 'SiSh', 'MS',
                 'WS', 'D','PS', 'BS']
#facies_color_map is a dictionary that maps facies labels
#to their respective colors



    











In [36]:



    


training_data = pd.read_csv(facies_vector_path)
X = training_data[feature_names].values
y = training_data['Facies'].values
well = training_data['Well Name'].values
depth = training_data['Depth'].values



    











In [37]:



    


facies_color_map = {}
for ind, label in enumerate(facies_labels):
    facies_color_map[label] = facies_colors[ind]

def label_facies(row, labels):
    return labels[ row['Facies'] -1]
    
training_data.loc[:,'FaciesLabels'] = training_data.apply(lambda row: label_facies(row, facies_labels), axis=1)
training_data.describe()

# Fitering out some outliers
j = []
for i in range(len(training_data)):
    if ((training_data['NM_M'].values[i]==2)and ((training_data['Facies'].values[i]==1)or(training_data['Facies'].values[i]==2)or(training_data['Facies'].values[i]==3))):
        j.append(i)
    elif((training_data['NM_M'].values[i]==1)and((training_data['Facies'].values[i]!=1)and(training_data['Facies'].values[i]!=2)and(training_data['Facies'].values[i]!=3))):
        j.append(i)

training_data_filtered = training_data.drop(training_data.index[j])
print(np.shape(training_data_filtered))



    


















    






(4095, 12)










    






C:\Users\Cheols\Anaconda3\lib\site-packages\numpy\lib\function_base.py:4116: RuntimeWarning: Invalid value encountered in percentile
  interpolation=interpolation)

Add Missing PE by following AR4 Team





In [38]:



    


#X = training_data_filtered[feature_names].values
# Testing without filtering
X = training_data[feature_names].values

reg = RandomForestRegressor(max_features='sqrt', n_estimators=50)
# DataImpAll = training_data_filtered[feature_names].copy()
DataImpAll = training_data[feature_names].copy()
DataImp = DataImpAll.dropna(axis = 0, inplace=False)
Ximp=DataImp.loc[:, DataImp.columns != 'PE']
Yimp=DataImp.loc[:, 'PE']
reg.fit(Ximp, Yimp)
X[np.array(DataImpAll.PE.isnull()),4] = reg.predict(DataImpAll.loc[DataImpAll.PE.isnull(),:].drop('PE',axis=1,inplace=False))

2. Feature Selection

Log Plot of Facies

Filtered Data





In [39]:



    


#count the number of unique entries for each facies, sort them by
#facies number (instead of by number of entries)
#facies_counts_filtered = training_data_filtered['Facies'].value_counts().sort_index()
facies_counts = training_data['Facies'].value_counts().sort_index()
#use facies labels to index each count
#facies_counts_filtered.index = facies_labels
facies_counts.index = facies_labels

#facies_counts_filtered.plot(kind='bar',color=facies_colors, 
#                   title='Distribution of Filtered Training Data by Facies')
facies_counts.plot(kind='bar',color=facies_colors, 
                   title='Distribution of Filtered Training Data by Facies')
#facies_counts_filtered
#training_data_filtered.columns
#facies_counts_filtered

training_data.columns
facies_counts



    


















    
Out[39]:








SS      268
CSiS    940
FSiS    780
SiSh    271
MS      296
WS      582
D       141
PS      686
BS      185
Name: Facies, dtype: int64

Filtered facies





In [40]:



    


correct_facies_labels = training_data['Facies'].values
feature_vectors = training_data.drop(['Formation', 'Well Name', 'Depth','Facies','FaciesLabels'], axis=1)

Normailization





In [41]:



    


from sklearn import preprocessing
from sklearn.cross_validation import train_test_split
scaler = preprocessing.StandardScaler().fit(X)
scaled_features = scaler.transform(X)

3. Prediction Model

Accuracy





In [42]:



    


def accuracy(conf):
    total_correct = 0.
    nb_classes = conf.shape[0]
    for i in np.arange(0,nb_classes):
        total_correct += conf[i][i]
    acc = total_correct/sum(sum(conf))
    return acc



    











In [43]:



    


adjacent_facies = np.array([[1], [0,2], [1], [4], [3,5], [4,6,7], [5,7], [5,6,8], [6,7]])

def accuracy_adjacent(conf, adjacent_facies):
    nb_classes = conf.shape[0]
    total_correct = 0.
    for i in np.arange(0,nb_classes):
        total_correct += conf[i][i]
        for j in adjacent_facies[i]:
            total_correct += conf[i][j]
    return total_correct / sum(sum(conf))

Augment Features





In [44]:



    


# HouMath Team algorithm
# Feature windows concatenation function 

def augment_features_window(X, N_neig):
    
    # Parameters
    N_row = X.shape[0]
    N_feat = X.shape[1]

    # Zero padding
    X = np.vstack((np.zeros((N_neig, N_feat)), X, (np.zeros((N_neig, N_feat)))))

    # Loop over windows
    X_aug = np.zeros((N_row, N_feat*(2*N_neig+1)))
    for r in np.arange(N_row)+N_neig:
        this_row = []
        for c in np.arange(-N_neig,N_neig+1):
            this_row = np.hstack((this_row, X[r+c]))
        X_aug[r-N_neig] = this_row

    return X_aug



    











In [45]:



    


# HouMath Team algorithm
# Feature gradient computation function
def augment_features_gradient(X, depth):
    
    # Compute features gradient
    d_diff = np.diff(depth).reshape((-1, 1))
    d_diff[d_diff==0] = 0.001
    X_diff = np.diff(X, axis=0)
    X_grad = X_diff / d_diff
        
    # Compensate for last missing value
    X_grad = np.concatenate((X_grad, np.zeros((1, X_grad.shape[1]))))
    
    return X_grad



    











In [46]:



    


# HouMath Team algorithm
# Feature augmentation function
def augment_features(X, well, depth, N_neig=1):
    
    # Augment features
    X_aug = np.zeros((X.shape[0], X.shape[1]*(N_neig*2+2)))
    for w in np.unique(well):
        w_idx = np.where(well == w)[0]
        X_aug_win = augment_features_window(X[w_idx, :], N_neig)
        X_aug_grad = augment_features_gradient(X[w_idx, :], depth[w_idx])
        X_aug[w_idx, :] = np.concatenate((X_aug_win, X_aug_grad), axis=1)
    
    # Find padded rows
    padded_rows = np.unique(np.where(X_aug[:, 0:7] == np.zeros((1, 7)))[0])
    
    return X_aug, padded_rows



    











In [47]:



    


X_aug, padded_rows = augment_features(scaled_features, well, depth)
X_aug.shape



    


















    
Out[47]:








(4149, 28)

















In [48]:



    


from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X_aug, y, test_size=0.3, random_state=16)
X_train_full, X_test_zero, y_train_full, y_test_full = train_test_split(X_aug, y, test_size=0.0, random_state=42)
X_train_full.shape



    


















    
Out[48]:








(4149, 28)

SVM





In [49]:



    


from classification_utilities import display_cm, display_adj_cm
import sklearn.svm as svm



    











In [50]:



    


clf_filtered = svm.SVC(C=10, gamma=1)
clf_filtered.fit(X_train, y_train)



    


















    
Out[50]:








SVC(C=10, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape=None, degree=3, gamma=1, kernel='rbf',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)

















In [51]:



    


#predicted_labels_filtered = clf_filtered.predict(X_test_filtered)
predicted_labels = clf_filtered.predict(X_test)
cv_conf_svm = confusion_matrix(y_test, predicted_labels)
print('Optimized facies classification accuracy = %.2f' % accuracy(cv_conf_svm))
print('Optimized adjacent facies classification accuracy = %.2f' % accuracy_adjacent(cv_conf_svm, adjacent_facies))
display_cm(cv_conf_svm, facies_labels,display_metrics=True, hide_zeros=True)



    


















    






Optimized facies classification accuracy = 0.66
Optimized adjacent facies classification accuracy = 0.83
     Pred    SS  CSiS  FSiS  SiSh    MS    WS     D    PS    BS Total
     True
       SS    63    19     9           1                            92
     CSiS     3   198    92                                       293
     FSiS          24   200           1                 1         226
     SiSh                22    45     1     4           4          76
       MS                28     3    28    11     1    13          84
       WS                44     2     6   104          36         192
        D                19           1     3    12     5     1    41
       PS                48           1     6         138     1   194
       BS                10     1                       3    33    47

Precision  0.95  0.82  0.42  0.88  0.72  0.81  0.92  0.69  0.94  0.74
   Recall  0.68  0.68  0.88  0.59  0.33  0.54  0.29  0.71  0.70  0.66
       F1  0.80  0.74  0.57  0.71  0.46  0.65  0.44  0.70  0.80  0.67

4. Result Analysis

Prepare test data





In [52]:



    


well_data = pd.read_csv('validation_data_nofacies.csv')
well_data['Well Name'] = well_data['Well Name'].astype('category')
well_features = well_data.drop(['Formation', 'Well Name', 'Depth'], axis=1)
# Prepare test data
well_ts = well_data['Well Name'].values
depth_ts = well_data['Depth'].values
X_ts = well_data[feature_names].values
X_ts = scaler.transform(X_ts)
# Augment features
X_ts, padded_rows = augment_features(X_ts, well_ts, depth_ts)



    











In [53]:



    


# Using all data and optimize parameter to train the data
clf_filtered = svm.SVC(C=10, gamma=1)
clf_filtered.fit(X_train_full, y_train_full)
#clf_filtered.fit(X_train_filtered, y_train_filtered)
y_pred = clf_filtered.predict(X_ts)
well_data['Facies'] = y_pred
well_data
well_data.to_csv('predict_result_svm_full_data.csv')

5. Using Tensorflow

Filtered Data Model





In [54]:



    


X_train.shape



    


















    
Out[54]:








(2904, 28)

















In [102]:



    


from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf

# Specify that all features have real-value data
# feature_columns_filtered = [tf.contrib.layers.real_valued_column("", dimension=7)]
feature_columns_filtered = [tf.contrib.layers.real_valued_column("", dimension=28)]

# Build DNN 
classifier_filtered = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns_filtered,
                                            hidden_units=[7,14],
                                            n_classes=10)

classifier_filtered.fit(x=X_train,y=y_train,steps=5000)
y_predict = []
predictions = classifier_filtered.predict(x=X_test)


for i, p in enumerate(predictions):
    y_predict.append(p)
    #print("Index %s: Prediction - %s, Real - %s" % (i + 1, p, y_test_filtered[i]))

# Evaluate accuracy.
accuracy_score = classifier_filtered.evaluate(x=X_test, y=y_test)["accuracy"]
print('Accuracy: {0:f}'.format(accuracy_score))

cv_conf_dnn = confusion_matrix(y_test, y_predict)

print('Optimized facies classification accuracy = %.2f' % accuracy(cv_conf_dnn))
print('Optimized adjacent facies classification accuracy = %.2f' % accuracy_adjacent(cv_conf_dnn, adjacent_facies))
display_cm(cv_conf_dnn, facies_labels,display_metrics=True, hide_zeros=True)



    


















    






WARNING:tensorflow:Using temporary folder as model directory: C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj
INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_master': '', 'save_summary_steps': 100, '_is_chief': True, 'keep_checkpoint_every_n_hours': 10000, 'keep_checkpoint_max': 5, 'tf_random_seed': None, '_environment': 'local', '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x0000022A68421400>, '_num_ps_replicas': 0, 'tf_config': gpu_options {
  per_process_gpu_memory_fraction: 1
}
, 'save_checkpoints_steps': None, '_task_id': 0, 'save_checkpoints_secs': 600, '_evaluation_master': '', '_task_type': None}
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with y is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:loss = 2.298, step = 1
INFO:tensorflow:Saving checkpoints for 1 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:loss = 1.17959, step = 101
INFO:tensorflow:global_step/sec: 79.2778
INFO:tensorflow:loss = 1.09614, step = 201
INFO:tensorflow:global_step/sec: 110.57
INFO:tensorflow:loss = 1.0561, step = 301
INFO:tensorflow:global_step/sec: 110.715
INFO:tensorflow:loss = 1.02479, step = 401
INFO:tensorflow:global_step/sec: 111.809
INFO:tensorflow:loss = 0.999477, step = 501
INFO:tensorflow:global_step/sec: 90.585
INFO:tensorflow:loss = 0.981072, step = 601
INFO:tensorflow:global_step/sec: 91.9208
INFO:tensorflow:loss = 0.965971, step = 701
INFO:tensorflow:global_step/sec: 97.5874
INFO:tensorflow:loss = 0.953984, step = 801
INFO:tensorflow:global_step/sec: 103.566
INFO:tensorflow:loss = 0.944553, step = 901
INFO:tensorflow:global_step/sec: 110.57
INFO:tensorflow:loss = 0.9368, step = 1001
INFO:tensorflow:global_step/sec: 111.309
INFO:tensorflow:loss = 0.930213, step = 1101
INFO:tensorflow:global_step/sec: 105.652
INFO:tensorflow:loss = 0.924678, step = 1201
INFO:tensorflow:global_step/sec: 112.949
INFO:tensorflow:loss = 0.920047, step = 1301
INFO:tensorflow:global_step/sec: 103.998
INFO:tensorflow:loss = 0.915487, step = 1401
INFO:tensorflow:global_step/sec: 108.999
INFO:tensorflow:loss = 0.911635, step = 1501
INFO:tensorflow:global_step/sec: 109.596
INFO:tensorflow:loss = 0.907936, step = 1601
INFO:tensorflow:global_step/sec: 108.882
INFO:tensorflow:loss = 0.904682, step = 1701
INFO:tensorflow:global_step/sec: 104.543
INFO:tensorflow:loss = 0.901504, step = 1801
INFO:tensorflow:global_step/sec: 88.2606
INFO:tensorflow:loss = 0.898273, step = 1901
INFO:tensorflow:global_step/sec: 108.171
INFO:tensorflow:loss = 0.894641, step = 2001
INFO:tensorflow:global_step/sec: 111.311
INFO:tensorflow:loss = 0.890842, step = 2101
INFO:tensorflow:global_step/sec: 108.172
INFO:tensorflow:loss = 0.887401, step = 2201
INFO:tensorflow:global_step/sec: 110.57
INFO:tensorflow:loss = 0.88462, step = 2301
INFO:tensorflow:global_step/sec: 110.326
INFO:tensorflow:loss = 0.881631, step = 2401
INFO:tensorflow:global_step/sec: 111.437
INFO:tensorflow:loss = 0.879085, step = 2501
INFO:tensorflow:global_step/sec: 112.44
INFO:tensorflow:loss = 0.876797, step = 2601
INFO:tensorflow:global_step/sec: 111.684
INFO:tensorflow:loss = 0.874376, step = 2701
INFO:tensorflow:global_step/sec: 107.355
INFO:tensorflow:loss = 0.872057, step = 2801
INFO:tensorflow:global_step/sec: 109.599
INFO:tensorflow:loss = 0.869924, step = 2901
INFO:tensorflow:global_step/sec: 111.809
INFO:tensorflow:loss = 0.869674, step = 3001
INFO:tensorflow:global_step/sec: 113.852
INFO:tensorflow:loss = 0.866181, step = 3101
INFO:tensorflow:global_step/sec: 110.203
INFO:tensorflow:loss = 0.864303, step = 3201
INFO:tensorflow:global_step/sec: 111.413
INFO:tensorflow:loss = 0.864604, step = 3301
INFO:tensorflow:global_step/sec: 114.5
INFO:tensorflow:loss = 0.860986, step = 3401
INFO:tensorflow:global_step/sec: 113.039
INFO:tensorflow:loss = 0.859248, step = 3501
INFO:tensorflow:global_step/sec: 113.205
INFO:tensorflow:loss = 0.857519, step = 3601
INFO:tensorflow:global_step/sec: 114.374
INFO:tensorflow:loss = 0.856029, step = 3701
INFO:tensorflow:global_step/sec: 115.567
INFO:tensorflow:loss = 0.854658, step = 3801
INFO:tensorflow:global_step/sec: 113.077
INFO:tensorflow:loss = 0.853313, step = 3901
INFO:tensorflow:global_step/sec: 115.567
INFO:tensorflow:loss = 0.852006, step = 4001
INFO:tensorflow:global_step/sec: 114.769
INFO:tensorflow:loss = 0.850683, step = 4101
INFO:tensorflow:global_step/sec: 113.592
INFO:tensorflow:loss = 0.849467, step = 4201
INFO:tensorflow:global_step/sec: 116.375
INFO:tensorflow:loss = 0.84826, step = 4301
INFO:tensorflow:global_step/sec: 115.702
INFO:tensorflow:loss = 0.846906, step = 4401
INFO:tensorflow:global_step/sec: 113.351
INFO:tensorflow:loss = 0.845546, step = 4501
INFO:tensorflow:global_step/sec: 113.97
INFO:tensorflow:loss = 0.843841, step = 4601
INFO:tensorflow:global_step/sec: 113.408
INFO:tensorflow:loss = 0.842527, step = 4701
INFO:tensorflow:global_step/sec: 114.901
INFO:tensorflow:loss = 0.841063, step = 4801
INFO:tensorflow:global_step/sec: 114.112
INFO:tensorflow:loss = 0.839575, step = 4901
INFO:tensorflow:global_step/sec: 113.85
INFO:tensorflow:Saving checkpoints for 5000 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:Loss for final step: 0.838111.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with as_iterable is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Loading model from checkpoint: C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt-5000-?????-of-00001.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:323 in evaluate.: calling BaseEstimator.evaluate (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:323 in evaluate.: calling BaseEstimator.evaluate (from tensorflow.contrib.learn.python.learn.estimators.estimator) with y is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:323 in evaluate.: calling BaseEstimator.evaluate (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Restored model from C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj
INFO:tensorflow:Eval steps [0,inf) for training step 5000.
INFO:tensorflow:Input iterator is exhausted.
INFO:tensorflow:Saving evaluation summary for step 5000: accuracy = 0.595984, loss = 1.03088
Accuracy: 0.595984
Optimized facies classification accuracy = 0.60
Optimized adjacent facies classification accuracy = 0.91
     Pred    SS  CSiS  FSiS  SiSh    MS    WS     D    PS    BS Total
     True
       SS    38    52     2                                        92
     CSiS    10   217    63           1                 2         293
     FSiS          76   143     1     1     2           3         226
     SiSh                 2    50     1    18     2     3          76
       MS           1          11    25    30     3    14          84
       WS                 1    22    21    97     6    45         192
        D                       1     1     2    22    15          41
       PS           1     4     7    17    30     7   120     8   194
       BS                       1           1     1    14    30    47

Precision  0.79  0.63  0.67  0.54  0.37  0.54  0.54  0.56  0.79  0.60
   Recall  0.41  0.74  0.63  0.66  0.30  0.51  0.54  0.62  0.64  0.60
       F1  0.54  0.68  0.65  0.59  0.33  0.52  0.54  0.59  0.71  0.59

Result from DNN





In [107]:



    


multirun=5
dnn_result_array = np.zeros((multirun,830))
for j in range(0,multirun):
    classifier_filtered.fit(x=X_train_full,
               y=y_train_full,
               steps=10000)
    predictions = classifier_filtered.predict(X_ts)
    y_predict_filtered = []
    for i, p in enumerate(predictions):
        y_predict_filtered.append(p)
    dnn_result_array[j]=y_predict_filtered

final_prediction = []
from scipy.stats import mode
for k in range(0,830):
    pp = mode(dnn_result_array[0:multirun,k])[0][0]
    final_prediction.append(pp)
        
well_data['Facies'] = final_prediction
well_data
well_data.to_csv('predict_result_dnn_ModeResult.csv')



    


















    






WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with y is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:loss = 0.799244, step = 45001
INFO:tensorflow:Saving checkpoints for 45001 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:loss = 0.799195, step = 45101
INFO:tensorflow:global_step/sec: 63.4005
INFO:tensorflow:loss = 0.799174, step = 45201
INFO:tensorflow:global_step/sec: 79.9153
INFO:tensorflow:loss = 0.799114, step = 45301
INFO:tensorflow:global_step/sec: 75.3848
INFO:tensorflow:loss = 0.799096, step = 45401
INFO:tensorflow:global_step/sec: 79.0163
INFO:tensorflow:loss = 0.799074, step = 45501
INFO:tensorflow:global_step/sec: 81.4707
INFO:tensorflow:loss = 0.799049, step = 45601
INFO:tensorflow:global_step/sec: 79.0853
INFO:tensorflow:loss = 0.799015, step = 45701
INFO:tensorflow:global_step/sec: 80.7587
INFO:tensorflow:loss = 0.798973, step = 45801
INFO:tensorflow:global_step/sec: 79.2111
INFO:tensorflow:loss = 0.798971, step = 45901
INFO:tensorflow:global_step/sec: 81.6797
INFO:tensorflow:loss = 0.798966, step = 46001
INFO:tensorflow:global_step/sec: 81.6762
INFO:tensorflow:loss = 0.798886, step = 46101
INFO:tensorflow:global_step/sec: 83.1801
INFO:tensorflow:loss = 0.798938, step = 46201
INFO:tensorflow:global_step/sec: 83.1796
INFO:tensorflow:loss = 0.798816, step = 46301
INFO:tensorflow:global_step/sec: 82.976
INFO:tensorflow:loss = 0.798852, step = 46401
INFO:tensorflow:global_step/sec: 81.501
INFO:tensorflow:loss = 0.798809, step = 46501
INFO:tensorflow:global_step/sec: 82.6989
INFO:tensorflow:loss = 0.798792, step = 46601
INFO:tensorflow:global_step/sec: 83.6667
INFO:tensorflow:loss = 0.798768, step = 46701
INFO:tensorflow:global_step/sec: 83.8833
INFO:tensorflow:loss = 0.798763, step = 46801
INFO:tensorflow:global_step/sec: 81.743
INFO:tensorflow:loss = 0.798676, step = 46901
INFO:tensorflow:global_step/sec: 81.9685
INFO:tensorflow:loss = 0.798682, step = 47001
INFO:tensorflow:global_step/sec: 83.181
INFO:tensorflow:loss = 0.798639, step = 47101
INFO:tensorflow:global_step/sec: 83.0316
INFO:tensorflow:loss = 0.798621, step = 47201
INFO:tensorflow:global_step/sec: 82.0195
INFO:tensorflow:loss = 0.798594, step = 47301
INFO:tensorflow:global_step/sec: 82.8357
INFO:tensorflow:loss = 0.798652, step = 47401
INFO:tensorflow:global_step/sec: 82.6981
INFO:tensorflow:loss = 0.79852, step = 47501
INFO:tensorflow:global_step/sec: 83.7837
INFO:tensorflow:loss = 0.798548, step = 47601
INFO:tensorflow:global_step/sec: 81.6156
INFO:tensorflow:loss = 0.798505, step = 47701
INFO:tensorflow:global_step/sec: 82.9728
INFO:tensorflow:loss = 0.798468, step = 47801
INFO:tensorflow:global_step/sec: 76.3667
INFO:tensorflow:loss = 0.79847, step = 47901
INFO:tensorflow:global_step/sec: 83.0425
INFO:tensorflow:loss = 0.798429, step = 48001
INFO:tensorflow:global_step/sec: 82.8955
INFO:tensorflow:loss = 0.798379, step = 48101
INFO:tensorflow:global_step/sec: 82.1963
INFO:tensorflow:loss = 0.798436, step = 48201
INFO:tensorflow:global_step/sec: 82.8357
INFO:tensorflow:loss = 0.798348, step = 48301
INFO:tensorflow:global_step/sec: 82.8357
INFO:tensorflow:loss = 0.798359, step = 48401
INFO:tensorflow:global_step/sec: 82.9735
INFO:tensorflow:loss = 0.798306, step = 48501
INFO:tensorflow:global_step/sec: 82.3544
INFO:tensorflow:loss = 0.798328, step = 48601
INFO:tensorflow:global_step/sec: 83.5293
INFO:tensorflow:loss = 0.798281, step = 48701
INFO:tensorflow:global_step/sec: 83.5216
INFO:tensorflow:loss = 0.798273, step = 48801
INFO:tensorflow:global_step/sec: 82.7483
INFO:tensorflow:loss = 0.798244, step = 48901
INFO:tensorflow:global_step/sec: 81.9536
INFO:tensorflow:loss = 0.798254, step = 49001
INFO:tensorflow:global_step/sec: 83.447
INFO:tensorflow:loss = 0.798186, step = 49101
INFO:tensorflow:global_step/sec: 81.9181
INFO:tensorflow:loss = 0.798155, step = 49201
INFO:tensorflow:global_step/sec: 83.1117
INFO:tensorflow:loss = 0.798111, step = 49301
INFO:tensorflow:global_step/sec: 82.2088
INFO:tensorflow:loss = 0.798064, step = 49401
INFO:tensorflow:global_step/sec: 82.0136
INFO:tensorflow:loss = 0.798056, step = 49501
INFO:tensorflow:global_step/sec: 84.2076
INFO:tensorflow:loss = 0.798111, step = 49601
INFO:tensorflow:global_step/sec: 83.9323
INFO:tensorflow:loss = 0.798002, step = 49701
INFO:tensorflow:global_step/sec: 82.9443
INFO:tensorflow:loss = 0.798043, step = 49801
INFO:tensorflow:global_step/sec: 83.3082
INFO:tensorflow:loss = 0.797952, step = 49901
INFO:tensorflow:global_step/sec: 83.1837
INFO:tensorflow:loss = 0.797941, step = 50001
INFO:tensorflow:global_step/sec: 81.6534
INFO:tensorflow:loss = 0.797891, step = 50101
INFO:tensorflow:global_step/sec: 81.2828
INFO:tensorflow:loss = 0.797912, step = 50201
INFO:tensorflow:global_step/sec: 83.7398
INFO:tensorflow:loss = 0.797878, step = 50301
INFO:tensorflow:global_step/sec: 82.5614
INFO:tensorflow:loss = 0.797868, step = 50401
INFO:tensorflow:global_step/sec: 78.8412
INFO:tensorflow:loss = 0.797805, step = 50501
INFO:tensorflow:global_step/sec: 82.6298
INFO:tensorflow:loss = 0.797804, step = 50601
INFO:tensorflow:global_step/sec: 85.0973
INFO:tensorflow:loss = 0.797769, step = 50701
INFO:tensorflow:global_step/sec: 84.808
INFO:tensorflow:loss = 0.797734, step = 50801
INFO:tensorflow:global_step/sec: 84.7613
INFO:tensorflow:loss = 0.79776, step = 50901
INFO:tensorflow:global_step/sec: 85.1698
INFO:tensorflow:loss = 0.797729, step = 51001
INFO:tensorflow:global_step/sec: 84.3751
INFO:tensorflow:loss = 0.797715, step = 51101
INFO:tensorflow:global_step/sec: 84.7383
INFO:tensorflow:loss = 0.797682, step = 51201
INFO:tensorflow:global_step/sec: 85.0247
INFO:tensorflow:loss = 0.797619, step = 51301
INFO:tensorflow:global_step/sec: 86.2007
INFO:tensorflow:loss = 0.797606, step = 51401
INFO:tensorflow:global_step/sec: 84.5205
INFO:tensorflow:loss = 0.797592, step = 51501
INFO:tensorflow:global_step/sec: 84.6506
INFO:tensorflow:loss = 0.797595, step = 51601
INFO:tensorflow:global_step/sec: 84.3062
INFO:tensorflow:loss = 0.797587, step = 51701
INFO:tensorflow:global_step/sec: 83.0107
INFO:tensorflow:loss = 0.797523, step = 51801
INFO:tensorflow:global_step/sec: 80.948
INFO:tensorflow:loss = 0.797514, step = 51901
INFO:tensorflow:global_step/sec: 71.2895
INFO:tensorflow:loss = 0.797488, step = 52001
INFO:tensorflow:global_step/sec: 79.9541
INFO:tensorflow:loss = 0.797453, step = 52101
INFO:tensorflow:global_step/sec: 79.2482
INFO:tensorflow:loss = 0.797465, step = 52201
INFO:tensorflow:global_step/sec: 80.3681
INFO:tensorflow:loss = 0.797477, step = 52301
INFO:tensorflow:global_step/sec: 79.2776
INFO:tensorflow:loss = 0.797417, step = 52401
INFO:tensorflow:global_step/sec: 81.6844
INFO:tensorflow:loss = 0.797397, step = 52501
INFO:tensorflow:global_step/sec: 81.7496
INFO:tensorflow:loss = 0.797375, step = 52601
INFO:tensorflow:global_step/sec: 80.6911
INFO:tensorflow:loss = 0.797388, step = 52701
INFO:tensorflow:global_step/sec: 80.8144
INFO:tensorflow:loss = 0.79733, step = 52801
INFO:tensorflow:global_step/sec: 80.0361
INFO:tensorflow:loss = 0.79732, step = 52901
INFO:tensorflow:global_step/sec: 82.1477
INFO:tensorflow:loss = 0.797301, step = 53001
INFO:tensorflow:global_step/sec: 81.0676
INFO:tensorflow:loss = 0.797263, step = 53101
INFO:tensorflow:global_step/sec: 80.8218
INFO:tensorflow:loss = 0.797283, step = 53201
INFO:tensorflow:global_step/sec: 81.5416
INFO:tensorflow:loss = 0.797305, step = 53301
INFO:tensorflow:global_step/sec: 82.4931
INFO:tensorflow:loss = 0.79723, step = 53401
INFO:tensorflow:global_step/sec: 78.6546
INFO:tensorflow:loss = 0.797234, step = 53501
INFO:tensorflow:global_step/sec: 81.48
INFO:tensorflow:loss = 0.797214, step = 53601
INFO:tensorflow:global_step/sec: 81.0881
INFO:tensorflow:loss = 0.797185, step = 53701
INFO:tensorflow:global_step/sec: 79.915
INFO:tensorflow:loss = 0.797193, step = 53801
INFO:tensorflow:global_step/sec: 78.7169
INFO:tensorflow:loss = 0.797133, step = 53901
INFO:tensorflow:global_step/sec: 80.8853
INFO:tensorflow:loss = 0.797122, step = 54001
INFO:tensorflow:global_step/sec: 80.6931
INFO:tensorflow:loss = 0.797088, step = 54101
INFO:tensorflow:global_step/sec: 82.4852
INFO:tensorflow:loss = 0.797101, step = 54201
INFO:tensorflow:global_step/sec: 77.6141
INFO:tensorflow:loss = 0.797138, step = 54301
INFO:tensorflow:global_step/sec: 79.9632
INFO:tensorflow:loss = 0.79705, step = 54401
INFO:tensorflow:global_step/sec: 80.9432
INFO:tensorflow:loss = 0.797033, step = 54501
INFO:tensorflow:global_step/sec: 81.344
INFO:tensorflow:loss = 0.797033, step = 54601
INFO:tensorflow:global_step/sec: 80.8875
INFO:tensorflow:loss = 0.796995, step = 54701
INFO:tensorflow:global_step/sec: 78.8412
INFO:tensorflow:loss = 0.796992, step = 54801
INFO:tensorflow:global_step/sec: 80.5007
INFO:tensorflow:loss = 0.796976, step = 54901
INFO:tensorflow:global_step/sec: 79.4062
INFO:tensorflow:Saving checkpoints for 55000 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:Loss for final step: 0.796938.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with as_iterable is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Loading model from checkpoint: C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt-55000-?????-of-00001.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with y is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:loss = 0.796968, step = 55001
INFO:tensorflow:Saving checkpoints for 55001 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:loss = 0.796914, step = 55101
INFO:tensorflow:global_step/sec: 65.1274
INFO:tensorflow:loss = 0.796903, step = 55201
INFO:tensorflow:global_step/sec: 78.8944
INFO:tensorflow:loss = 0.796877, step = 55301
INFO:tensorflow:global_step/sec: 79.8459
INFO:tensorflow:loss = 0.796871, step = 55401
INFO:tensorflow:global_step/sec: 80.0435
INFO:tensorflow:loss = 0.79684, step = 55501
INFO:tensorflow:global_step/sec: 79.9746
INFO:tensorflow:loss = 0.796817, step = 55601
INFO:tensorflow:global_step/sec: 78.9661
INFO:tensorflow:loss = 0.796796, step = 55701
INFO:tensorflow:global_step/sec: 78.9036
INFO:tensorflow:loss = 0.796763, step = 55801
INFO:tensorflow:global_step/sec: 79.4359
INFO:tensorflow:loss = 0.796732, step = 55901
INFO:tensorflow:global_step/sec: 80.9987
INFO:tensorflow:loss = 0.796699, step = 56001
INFO:tensorflow:global_step/sec: 78.1564
INFO:tensorflow:loss = 0.796681, step = 56101
INFO:tensorflow:global_step/sec: 79.3358
INFO:tensorflow:loss = 0.796653, step = 56201
INFO:tensorflow:global_step/sec: 78.9661
INFO:tensorflow:loss = 0.796642, step = 56301
INFO:tensorflow:global_step/sec: 79.502
INFO:tensorflow:loss = 0.796606, step = 56401
INFO:tensorflow:global_step/sec: 76.9437
INFO:tensorflow:loss = 0.796587, step = 56501
INFO:tensorflow:global_step/sec: 79.3431
INFO:tensorflow:loss = 0.796575, step = 56601
INFO:tensorflow:global_step/sec: 79.5318
INFO:tensorflow:loss = 0.796551, step = 56701
INFO:tensorflow:global_step/sec: 79.0922
INFO:tensorflow:loss = 0.796536, step = 56801
INFO:tensorflow:global_step/sec: 78.7026
INFO:tensorflow:loss = 0.796508, step = 56901
INFO:tensorflow:global_step/sec: 80.2937
INFO:tensorflow:loss = 0.79648, step = 57001
INFO:tensorflow:global_step/sec: 79.0533
INFO:tensorflow:loss = 0.796474, step = 57101
INFO:tensorflow:global_step/sec: 79.4695
INFO:tensorflow:loss = 0.796445, step = 57201
INFO:tensorflow:global_step/sec: 77.9153
INFO:tensorflow:loss = 0.796431, step = 57301
INFO:tensorflow:global_step/sec: 80.0746
INFO:tensorflow:loss = 0.796407, step = 57401
INFO:tensorflow:global_step/sec: 80.4305
INFO:tensorflow:loss = 0.796386, step = 57501
INFO:tensorflow:global_step/sec: 80.9606
INFO:tensorflow:loss = 0.796362, step = 57601
INFO:tensorflow:global_step/sec: 77.7025
INFO:tensorflow:loss = 0.796344, step = 57701
INFO:tensorflow:global_step/sec: 79.5306
INFO:tensorflow:loss = 0.796322, step = 57801
INFO:tensorflow:global_step/sec: 78.6541
INFO:tensorflow:loss = 0.796319, step = 57901
INFO:tensorflow:global_step/sec: 78.7167
INFO:tensorflow:loss = 0.796283, step = 58001
INFO:tensorflow:global_step/sec: 78.0672
INFO:tensorflow:loss = 0.796269, step = 58101
INFO:tensorflow:global_step/sec: 79.0833
INFO:tensorflow:loss = 0.796249, step = 58201
INFO:tensorflow:global_step/sec: 79.0918
INFO:tensorflow:loss = 0.796207, step = 58301
INFO:tensorflow:global_step/sec: 78.6787
INFO:tensorflow:loss = 0.796248, step = 58401
INFO:tensorflow:global_step/sec: 79.5252
INFO:tensorflow:loss = 0.796187, step = 58501
INFO:tensorflow:global_step/sec: 79.4172
INFO:tensorflow:loss = 0.79617, step = 58601
INFO:tensorflow:global_step/sec: 79.1969
INFO:tensorflow:loss = 0.796136, step = 58701
INFO:tensorflow:global_step/sec: 78.4689
INFO:tensorflow:loss = 0.796139, step = 58801
INFO:tensorflow:global_step/sec: 79.4627
INFO:tensorflow:loss = 0.796109, step = 58901
INFO:tensorflow:global_step/sec: 79.9152
INFO:tensorflow:loss = 0.796131, step = 59001
INFO:tensorflow:global_step/sec: 79.341
INFO:tensorflow:loss = 0.796079, step = 59101
INFO:tensorflow:global_step/sec: 78.9631
INFO:tensorflow:loss = 0.796076, step = 59201
INFO:tensorflow:global_step/sec: 80.2365
INFO:tensorflow:loss = 0.796049, step = 59301
INFO:tensorflow:global_step/sec: 79.0216
INFO:tensorflow:loss = 0.796026, step = 59401
INFO:tensorflow:global_step/sec: 78.841
INFO:tensorflow:loss = 0.796, step = 59501
INFO:tensorflow:global_step/sec: 77.9125
INFO:tensorflow:loss = 0.795988, step = 59601
INFO:tensorflow:global_step/sec: 78.8412
INFO:tensorflow:loss = 0.795957, step = 59701
INFO:tensorflow:global_step/sec: 79.278
INFO:tensorflow:loss = 0.795951, step = 59801
INFO:tensorflow:global_step/sec: 78.2861
INFO:tensorflow:loss = 0.795941, step = 59901
INFO:tensorflow:global_step/sec: 77.8458
INFO:tensorflow:loss = 0.795927, step = 60001
INFO:tensorflow:global_step/sec: 79.0332
INFO:tensorflow:loss = 0.795903, step = 60101
INFO:tensorflow:global_step/sec: 78.841
INFO:tensorflow:loss = 0.795906, step = 60201
INFO:tensorflow:global_step/sec: 79.1541
INFO:tensorflow:loss = 0.795852, step = 60301
INFO:tensorflow:global_step/sec: 78.176
INFO:tensorflow:loss = 0.795866, step = 60401
INFO:tensorflow:global_step/sec: 78.1614
INFO:tensorflow:loss = 0.795843, step = 60501
INFO:tensorflow:global_step/sec: 78.9034
INFO:tensorflow:loss = 0.79586, step = 60601
INFO:tensorflow:global_step/sec: 77.1782
INFO:tensorflow:loss = 0.79583, step = 60701
INFO:tensorflow:global_step/sec: 76.2492
INFO:tensorflow:loss = 0.795784, step = 60801
INFO:tensorflow:global_step/sec: 75.8847
INFO:tensorflow:loss = 0.795835, step = 60901
INFO:tensorflow:global_step/sec: 78.5307
INFO:tensorflow:loss = 0.795779, step = 61001
INFO:tensorflow:global_step/sec: 79.142
INFO:tensorflow:loss = 0.795743, step = 61101
INFO:tensorflow:global_step/sec: 78.3457
INFO:tensorflow:loss = 0.795734, step = 61201
INFO:tensorflow:global_step/sec: 76.8071
INFO:tensorflow:loss = 0.795721, step = 61301
INFO:tensorflow:global_step/sec: 77.4936
INFO:tensorflow:loss = 0.795715, step = 61401
INFO:tensorflow:global_step/sec: 78.0372
INFO:tensorflow:loss = 0.795704, step = 61501
INFO:tensorflow:global_step/sec: 77.6161
INFO:tensorflow:loss = 0.795671, step = 61601
INFO:tensorflow:global_step/sec: 77.6141
INFO:tensorflow:loss = 0.79568, step = 61701
INFO:tensorflow:global_step/sec: 77.0097
INFO:tensorflow:loss = 0.795659, step = 61801
INFO:tensorflow:global_step/sec: 79.4061
INFO:tensorflow:loss = 0.795626, step = 61901
INFO:tensorflow:global_step/sec: 77.3067
INFO:tensorflow:loss = 0.795623, step = 62001
INFO:tensorflow:global_step/sec: 77.315
INFO:tensorflow:loss = 0.795601, step = 62101
INFO:tensorflow:global_step/sec: 77.9071
INFO:tensorflow:loss = 0.795597, step = 62201
INFO:tensorflow:global_step/sec: 75.7857
INFO:tensorflow:loss = 0.795601, step = 62301
INFO:tensorflow:global_step/sec: 77.2534
INFO:tensorflow:loss = 0.795615, step = 62401
INFO:tensorflow:global_step/sec: 79.8881
INFO:tensorflow:loss = 0.79554, step = 62501
INFO:tensorflow:global_step/sec: 80.0432
INFO:tensorflow:loss = 0.795544, step = 62601
INFO:tensorflow:global_step/sec: 75.4989
INFO:tensorflow:loss = 0.795543, step = 62701
INFO:tensorflow:global_step/sec: 76.4248
INFO:tensorflow:loss = 0.795532, step = 62801
INFO:tensorflow:global_step/sec: 77.1339
INFO:tensorflow:loss = 0.795487, step = 62901
INFO:tensorflow:global_step/sec: 78.8605
INFO:tensorflow:loss = 0.795475, step = 63001
INFO:tensorflow:global_step/sec: 78.5239
INFO:tensorflow:loss = 0.795447, step = 63101
INFO:tensorflow:global_step/sec: 77.8565
INFO:tensorflow:loss = 0.795439, step = 63201
INFO:tensorflow:global_step/sec: 78.3908
INFO:tensorflow:loss = 0.79543, step = 63301
INFO:tensorflow:global_step/sec: 79.9172
INFO:tensorflow:loss = 0.795426, step = 63401
INFO:tensorflow:global_step/sec: 77.0725
INFO:tensorflow:loss = 0.795403, step = 63501
INFO:tensorflow:global_step/sec: 78.8432
INFO:tensorflow:loss = 0.795379, step = 63601
INFO:tensorflow:global_step/sec: 77.2259
INFO:tensorflow:loss = 0.795386, step = 63701
INFO:tensorflow:global_step/sec: 78.4211
INFO:tensorflow:loss = 0.795369, step = 63801
INFO:tensorflow:global_step/sec: 75.6707
INFO:tensorflow:loss = 0.795347, step = 63901
INFO:tensorflow:global_step/sec: 78.0093
INFO:tensorflow:loss = 0.795345, step = 64001
INFO:tensorflow:global_step/sec: 77.0714
INFO:tensorflow:loss = 0.795315, step = 64101
INFO:tensorflow:global_step/sec: 75.7858
INFO:tensorflow:loss = 0.795313, step = 64201
INFO:tensorflow:global_step/sec: 74.953
INFO:tensorflow:loss = 0.795297, step = 64301
INFO:tensorflow:global_step/sec: 77.0742
INFO:tensorflow:loss = 0.795279, step = 64401
INFO:tensorflow:global_step/sec: 76.6007
INFO:tensorflow:loss = 0.795262, step = 64501
INFO:tensorflow:global_step/sec: 78.2209
INFO:tensorflow:loss = 0.795255, step = 64601
INFO:tensorflow:global_step/sec: 75.6727
INFO:tensorflow:loss = 0.795225, step = 64701
INFO:tensorflow:global_step/sec: 77.8563
INFO:tensorflow:loss = 0.795215, step = 64801
INFO:tensorflow:global_step/sec: 76.9053
INFO:tensorflow:loss = 0.795188, step = 64901
INFO:tensorflow:global_step/sec: 76.6595
INFO:tensorflow:Saving checkpoints for 65000 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:Loss for final step: 0.795183.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with as_iterable is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Loading model from checkpoint: C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt-65000-?????-of-00001.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with y is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:loss = 0.795178, step = 65001
INFO:tensorflow:Saving checkpoints for 65001 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:loss = 0.795171, step = 65101
INFO:tensorflow:global_step/sec: 58.046
INFO:tensorflow:loss = 0.795163, step = 65201
INFO:tensorflow:global_step/sec: 75.101
INFO:tensorflow:loss = 0.79516, step = 65301
INFO:tensorflow:global_step/sec: 75.6115
INFO:tensorflow:loss = 0.795134, step = 65401
INFO:tensorflow:global_step/sec: 75.8434
INFO:tensorflow:loss = 0.795126, step = 65501
INFO:tensorflow:global_step/sec: 74.99
INFO:tensorflow:loss = 0.795103, step = 65601
INFO:tensorflow:global_step/sec: 78.7762
INFO:tensorflow:loss = 0.795095, step = 65701
INFO:tensorflow:global_step/sec: 77.918
INFO:tensorflow:loss = 0.79506, step = 65801
INFO:tensorflow:global_step/sec: 76.9572
INFO:tensorflow:loss = 0.795074, step = 65901
INFO:tensorflow:global_step/sec: 76.6008
INFO:tensorflow:loss = 0.795071, step = 66001
INFO:tensorflow:global_step/sec: 76.366
INFO:tensorflow:loss = 0.795035, step = 66101
INFO:tensorflow:global_step/sec: 75.7878
INFO:tensorflow:loss = 0.795027, step = 66201
INFO:tensorflow:global_step/sec: 77.8562
INFO:tensorflow:loss = 0.794928, step = 66301
INFO:tensorflow:global_step/sec: 75.8807
INFO:tensorflow:loss = 0.79488, step = 66401
INFO:tensorflow:global_step/sec: 76.7184
INFO:tensorflow:loss = 0.794849, step = 66501
INFO:tensorflow:global_step/sec: 77.9783
INFO:tensorflow:loss = 0.794815, step = 66601
INFO:tensorflow:global_step/sec: 76.542
INFO:tensorflow:loss = 0.794811, step = 66701
INFO:tensorflow:global_step/sec: 77.851
INFO:tensorflow:loss = 0.794766, step = 66801
INFO:tensorflow:global_step/sec: 77.2532
INFO:tensorflow:loss = 0.794763, step = 66901
INFO:tensorflow:global_step/sec: 77.3734
INFO:tensorflow:loss = 0.794756, step = 67001
INFO:tensorflow:global_step/sec: 77.8516
INFO:tensorflow:loss = 0.794723, step = 67101
INFO:tensorflow:global_step/sec: 76.7777
INFO:tensorflow:loss = 0.794692, step = 67201
INFO:tensorflow:global_step/sec: 79.6612
INFO:tensorflow:loss = 0.794698, step = 67301
INFO:tensorflow:global_step/sec: 76.3075
INFO:tensorflow:loss = 0.794694, step = 67401
INFO:tensorflow:global_step/sec: 76.0749
INFO:tensorflow:loss = 0.794676, step = 67501
INFO:tensorflow:global_step/sec: 75.556
INFO:tensorflow:loss = 0.794631, step = 67601
INFO:tensorflow:global_step/sec: 78.5929
INFO:tensorflow:loss = 0.794623, step = 67701
INFO:tensorflow:global_step/sec: 77.1934
INFO:tensorflow:loss = 0.79459, step = 67801
INFO:tensorflow:global_step/sec: 75.2711
INFO:tensorflow:loss = 0.794581, step = 67901
INFO:tensorflow:global_step/sec: 77.7352
INFO:tensorflow:loss = 0.794561, step = 68001
INFO:tensorflow:global_step/sec: 76.9683
INFO:tensorflow:loss = 0.794549, step = 68101
INFO:tensorflow:global_step/sec: 78.7789
INFO:tensorflow:loss = 0.794527, step = 68201
INFO:tensorflow:global_step/sec: 75.499
INFO:tensorflow:loss = 0.794513, step = 68301
INFO:tensorflow:global_step/sec: 79.4062
INFO:tensorflow:loss = 0.794499, step = 68401
INFO:tensorflow:global_step/sec: 76.1866
INFO:tensorflow:loss = 0.794492, step = 68501
INFO:tensorflow:global_step/sec: 76.6008
INFO:tensorflow:loss = 0.794469, step = 68601
INFO:tensorflow:global_step/sec: 74.8193
INFO:tensorflow:loss = 0.794467, step = 68701
INFO:tensorflow:global_step/sec: 76.9468
INFO:tensorflow:loss = 0.79444, step = 68801
INFO:tensorflow:global_step/sec: 76.1905
INFO:tensorflow:loss = 0.794434, step = 68901
INFO:tensorflow:global_step/sec: 77.7367
INFO:tensorflow:loss = 0.7944, step = 69001
INFO:tensorflow:global_step/sec: 74.2605
INFO:tensorflow:loss = 0.794378, step = 69101
INFO:tensorflow:global_step/sec: 76.0518
INFO:tensorflow:loss = 0.794384, step = 69201
INFO:tensorflow:global_step/sec: 76.4228
INFO:tensorflow:loss = 0.794317, step = 69301
INFO:tensorflow:global_step/sec: 77.1956
INFO:tensorflow:loss = 0.794315, step = 69401
INFO:tensorflow:global_step/sec: 77.4934
INFO:tensorflow:loss = 0.79429, step = 69501
INFO:tensorflow:global_step/sec: 76.6008
INFO:tensorflow:loss = 0.794267, step = 69601
INFO:tensorflow:global_step/sec: 76.441
INFO:tensorflow:loss = 0.794266, step = 69701
INFO:tensorflow:global_step/sec: 75.7281
INFO:tensorflow:loss = 0.794254, step = 69801
INFO:tensorflow:global_step/sec: 76.2266
INFO:tensorflow:loss = 0.79426, step = 69901
INFO:tensorflow:global_step/sec: 76.7775
INFO:tensorflow:loss = 0.79422, step = 70001
INFO:tensorflow:global_step/sec: 76.7776
INFO:tensorflow:loss = 0.794187, step = 70101
INFO:tensorflow:global_step/sec: 75.0444
INFO:tensorflow:loss = 0.794183, step = 70201
INFO:tensorflow:global_step/sec: 76.0749
INFO:tensorflow:loss = 0.794168, step = 70301
INFO:tensorflow:global_step/sec: 77.1917
INFO:tensorflow:loss = 0.794119, step = 70401
INFO:tensorflow:global_step/sec: 66.0068
INFO:tensorflow:loss = 0.794106, step = 70501
INFO:tensorflow:global_step/sec: 75.1575
INFO:tensorflow:loss = 0.79409, step = 70601
INFO:tensorflow:global_step/sec: 77.1936
INFO:tensorflow:loss = 0.794069, step = 70701
INFO:tensorflow:global_step/sec: 76.075
INFO:tensorflow:loss = 0.794019, step = 70801
INFO:tensorflow:global_step/sec: 74.9317
INFO:tensorflow:loss = 0.79407, step = 70901
INFO:tensorflow:global_step/sec: 76.7186
INFO:tensorflow:loss = 0.793968, step = 71001
INFO:tensorflow:global_step/sec: 75.959
INFO:tensorflow:loss = 0.793956, step = 71101
INFO:tensorflow:global_step/sec: 76.6595
INFO:tensorflow:loss = 0.793953, step = 71201
INFO:tensorflow:global_step/sec: 75.2711
INFO:tensorflow:loss = 0.793932, step = 71301
INFO:tensorflow:global_step/sec: 77.0743
INFO:tensorflow:loss = 0.793916, step = 71401
INFO:tensorflow:global_step/sec: 76.8916
INFO:tensorflow:loss = 0.793923, step = 71501
INFO:tensorflow:global_step/sec: 76.3639
INFO:tensorflow:loss = 0.793882, step = 71601
INFO:tensorflow:global_step/sec: 75.387
INFO:tensorflow:loss = 0.79386, step = 71701
INFO:tensorflow:global_step/sec: 75.1577
INFO:tensorflow:loss = 0.793891, step = 71801
INFO:tensorflow:global_step/sec: 76.1329
INFO:tensorflow:loss = 0.793808, step = 71901
INFO:tensorflow:global_step/sec: 77.1936
INFO:tensorflow:loss = 0.793872, step = 72001
INFO:tensorflow:global_step/sec: 74.9314
INFO:tensorflow:loss = 0.793814, step = 72101
INFO:tensorflow:global_step/sec: 74.1456
INFO:tensorflow:loss = 0.79379, step = 72201
INFO:tensorflow:global_step/sec: 75.8387
INFO:tensorflow:loss = 0.793774, step = 72301
INFO:tensorflow:global_step/sec: 76.7776
INFO:tensorflow:loss = 0.793767, step = 72401
INFO:tensorflow:global_step/sec: 75.3614
INFO:tensorflow:loss = 0.793742, step = 72501
INFO:tensorflow:global_step/sec: 77.1935
INFO:tensorflow:loss = 0.793737, step = 72601
INFO:tensorflow:global_step/sec: 76.9553
INFO:tensorflow:loss = 0.793715, step = 72701
INFO:tensorflow:global_step/sec: 74.7071
INFO:tensorflow:loss = 0.793718, step = 72801
INFO:tensorflow:global_step/sec: 76.8368
INFO:tensorflow:loss = 0.793751, step = 72901
INFO:tensorflow:global_step/sec: 77.0131
INFO:tensorflow:loss = 0.793681, step = 73001
INFO:tensorflow:global_step/sec: 75.9842
INFO:tensorflow:loss = 0.793647, step = 73101
INFO:tensorflow:global_step/sec: 75.8433
INFO:tensorflow:loss = 0.793636, step = 73201
INFO:tensorflow:global_step/sec: 75.7281
INFO:tensorflow:loss = 0.793649, step = 73301
INFO:tensorflow:global_step/sec: 76.1906
INFO:tensorflow:loss = 0.793623, step = 73401
INFO:tensorflow:global_step/sec: 77.0154
INFO:tensorflow:loss = 0.793626, step = 73501
INFO:tensorflow:global_step/sec: 74.9683
INFO:tensorflow:loss = 0.793648, step = 73601
INFO:tensorflow:global_step/sec: 75.3847
INFO:tensorflow:loss = 0.793581, step = 73701
INFO:tensorflow:global_step/sec: 76.7167
INFO:tensorflow:loss = 0.793578, step = 73801
INFO:tensorflow:global_step/sec: 73.9885
INFO:tensorflow:loss = 0.793559, step = 73901
INFO:tensorflow:global_step/sec: 73.0653
INFO:tensorflow:loss = 0.793559, step = 74001
INFO:tensorflow:global_step/sec: 75.2124
INFO:tensorflow:loss = 0.793553, step = 74101
INFO:tensorflow:global_step/sec: 76.1348
INFO:tensorflow:loss = 0.793552, step = 74201
INFO:tensorflow:global_step/sec: 75.2711
INFO:tensorflow:loss = 0.79352, step = 74301
INFO:tensorflow:global_step/sec: 75.499
INFO:tensorflow:loss = 0.793521, step = 74401
INFO:tensorflow:global_step/sec: 75.2143
INFO:tensorflow:loss = 0.793518, step = 74501
INFO:tensorflow:global_step/sec: 75.8365
INFO:tensorflow:loss = 0.793467, step = 74601
INFO:tensorflow:global_step/sec: 76.133
INFO:tensorflow:loss = 0.793423, step = 74701
INFO:tensorflow:global_step/sec: 76.6576
INFO:tensorflow:loss = 0.79338, step = 74801
INFO:tensorflow:global_step/sec: 76.4851
INFO:tensorflow:loss = 0.793365, step = 74901
INFO:tensorflow:global_step/sec: 68.6403
INFO:tensorflow:Saving checkpoints for 75000 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:Loss for final step: 0.793344.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with as_iterable is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Loading model from checkpoint: C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt-75000-?????-of-00001.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with y is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:loss = 0.793342, step = 75001
INFO:tensorflow:Saving checkpoints for 75001 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:loss = 0.793336, step = 75101
INFO:tensorflow:global_step/sec: 59.5314
INFO:tensorflow:loss = 0.793312, step = 75201
INFO:tensorflow:global_step/sec: 76.6595
INFO:tensorflow:loss = 0.793282, step = 75301
INFO:tensorflow:global_step/sec: 75.7282
INFO:tensorflow:loss = 0.7933, step = 75401
INFO:tensorflow:global_step/sec: 75.8047
INFO:tensorflow:loss = 0.793274, step = 75501
INFO:tensorflow:global_step/sec: 75.214
INFO:tensorflow:loss = 0.793271, step = 75601
INFO:tensorflow:global_step/sec: 76.0731
INFO:tensorflow:loss = 0.793236, step = 75701
INFO:tensorflow:global_step/sec: 74.3194
INFO:tensorflow:loss = 0.793236, step = 75801
INFO:tensorflow:global_step/sec: 75.3279
INFO:tensorflow:loss = 0.793207, step = 75901
INFO:tensorflow:global_step/sec: 74.0416
INFO:tensorflow:loss = 0.79321, step = 76001
INFO:tensorflow:global_step/sec: 75.5562
INFO:tensorflow:loss = 0.793183, step = 76101
INFO:tensorflow:global_step/sec: 75.1513
INFO:tensorflow:loss = 0.793181, step = 76201
INFO:tensorflow:global_step/sec: 75.9011
INFO:tensorflow:loss = 0.793152, step = 76301
INFO:tensorflow:global_step/sec: 72.9763
INFO:tensorflow:loss = 0.793172, step = 76401
INFO:tensorflow:global_step/sec: 73.7132
INFO:tensorflow:loss = 0.793153, step = 76501
INFO:tensorflow:global_step/sec: 75.2736
INFO:tensorflow:loss = 0.793151, step = 76601
INFO:tensorflow:global_step/sec: 74.7631
INFO:tensorflow:loss = 0.793105, step = 76701
INFO:tensorflow:global_step/sec: 75.8433
INFO:tensorflow:loss = 0.793129, step = 76801
INFO:tensorflow:global_step/sec: 75.6709
INFO:tensorflow:loss = 0.793119, step = 76901
INFO:tensorflow:global_step/sec: 76.4439
INFO:tensorflow:loss = 0.79313, step = 77001
INFO:tensorflow:global_step/sec: 75.2708
INFO:tensorflow:loss = 0.793104, step = 77101
INFO:tensorflow:global_step/sec: 75.5245
INFO:tensorflow:loss = 0.793064, step = 77201
INFO:tensorflow:global_step/sec: 76.366
INFO:tensorflow:loss = 0.793069, step = 77301
INFO:tensorflow:global_step/sec: 74.5396
INFO:tensorflow:loss = 0.793059, step = 77401
INFO:tensorflow:global_step/sec: 74.3729
INFO:tensorflow:loss = 0.793065, step = 77501
INFO:tensorflow:global_step/sec: 76.1306
INFO:tensorflow:loss = 0.793029, step = 77601
INFO:tensorflow:global_step/sec: 74.5955
INFO:tensorflow:loss = 0.793044, step = 77701
INFO:tensorflow:global_step/sec: 76.1911
INFO:tensorflow:loss = 0.793035, step = 77801
INFO:tensorflow:global_step/sec: 75.101
INFO:tensorflow:loss = 0.793038, step = 77901
INFO:tensorflow:global_step/sec: 76.2493
INFO:tensorflow:loss = 0.793034, step = 78001
INFO:tensorflow:global_step/sec: 75.7283
INFO:tensorflow:loss = 0.793016, step = 78101
INFO:tensorflow:global_step/sec: 75.6628
INFO:tensorflow:loss = 0.793017, step = 78201
INFO:tensorflow:global_step/sec: 74.8774
INFO:tensorflow:loss = 0.793008, step = 78301
INFO:tensorflow:global_step/sec: 75.3277
INFO:tensorflow:loss = 0.792998, step = 78401
INFO:tensorflow:global_step/sec: 75.5848
INFO:tensorflow:loss = 0.792983, step = 78501
INFO:tensorflow:global_step/sec: 73.9948
INFO:tensorflow:loss = 0.792976, step = 78601
INFO:tensorflow:global_step/sec: 74.6511
INFO:tensorflow:loss = 0.792983, step = 78701
INFO:tensorflow:global_step/sec: 75.5563
INFO:tensorflow:loss = 0.79297, step = 78801
INFO:tensorflow:global_step/sec: 76.8054
INFO:tensorflow:loss = 0.792953, step = 78901
INFO:tensorflow:global_step/sec: 74.4841
INFO:tensorflow:loss = 0.792925, step = 79001
INFO:tensorflow:global_step/sec: 74.8753
INFO:tensorflow:loss = 0.792933, step = 79101
INFO:tensorflow:global_step/sec: 74.7569
INFO:tensorflow:loss = 0.792947, step = 79201
INFO:tensorflow:global_step/sec: 75.7858
INFO:tensorflow:loss = 0.792947, step = 79301
INFO:tensorflow:global_step/sec: 71.6954
INFO:tensorflow:loss = 0.792908, step = 79401
INFO:tensorflow:global_step/sec: 72.6926
INFO:tensorflow:loss = 0.792896, step = 79501
INFO:tensorflow:global_step/sec: 62.5852
INFO:tensorflow:loss = 0.792901, step = 79601
INFO:tensorflow:global_step/sec: 60.2258
INFO:tensorflow:loss = 0.792885, step = 79701
INFO:tensorflow:global_step/sec: 60.6287
INFO:tensorflow:loss = 0.792896, step = 79801
INFO:tensorflow:global_step/sec: 64.7574
INFO:tensorflow:loss = 0.792877, step = 79901
INFO:tensorflow:global_step/sec: 63.5654
INFO:tensorflow:loss = 0.79287, step = 80001
INFO:tensorflow:global_step/sec: 67.1125
INFO:tensorflow:loss = 0.792844, step = 80101
INFO:tensorflow:global_step/sec: 72.0895
INFO:tensorflow:loss = 0.79286, step = 80201
INFO:tensorflow:global_step/sec: 71.7011
INFO:tensorflow:loss = 0.792859, step = 80301
INFO:tensorflow:global_step/sec: 71.0823
INFO:tensorflow:loss = 0.792844, step = 80401
INFO:tensorflow:global_step/sec: 74.3729
INFO:tensorflow:loss = 0.792838, step = 80501
INFO:tensorflow:global_step/sec: 75.499
INFO:tensorflow:loss = 0.792847, step = 80601
INFO:tensorflow:global_step/sec: 72.7455
INFO:tensorflow:loss = 0.792823, step = 80701
INFO:tensorflow:global_step/sec: 74.2604
INFO:tensorflow:loss = 0.792826, step = 80801
INFO:tensorflow:global_step/sec: 73.9775
INFO:tensorflow:loss = 0.792808, step = 80901
INFO:tensorflow:global_step/sec: 74.2061
INFO:tensorflow:loss = 0.792806, step = 81001
INFO:tensorflow:global_step/sec: 74.0969
INFO:tensorflow:loss = 0.7928, step = 81101
INFO:tensorflow:global_step/sec: 74.0332
INFO:tensorflow:loss = 0.792799, step = 81201
INFO:tensorflow:global_step/sec: 73.1701
INFO:tensorflow:loss = 0.792775, step = 81301
INFO:tensorflow:global_step/sec: 72.9478
INFO:tensorflow:loss = 0.792776, step = 81401
INFO:tensorflow:global_step/sec: 71.0357
INFO:tensorflow:loss = 0.792773, step = 81501
INFO:tensorflow:global_step/sec: 74.4285
INFO:tensorflow:loss = 0.792766, step = 81601
INFO:tensorflow:global_step/sec: 73.3273
INFO:tensorflow:loss = 0.79277, step = 81701
INFO:tensorflow:global_step/sec: 71.2896
INFO:tensorflow:loss = 0.792763, step = 81801
INFO:tensorflow:global_step/sec: 73.4421
INFO:tensorflow:loss = 0.792748, step = 81901
INFO:tensorflow:global_step/sec: 63.4767
INFO:tensorflow:loss = 0.792749, step = 82001
INFO:tensorflow:global_step/sec: 72.4799
INFO:tensorflow:loss = 0.792745, step = 82101
INFO:tensorflow:global_step/sec: 72.443
INFO:tensorflow:loss = 0.792727, step = 82201
INFO:tensorflow:global_step/sec: 72.2677
INFO:tensorflow:loss = 0.792724, step = 82301
INFO:tensorflow:global_step/sec: 72.1142
INFO:tensorflow:loss = 0.792735, step = 82401
INFO:tensorflow:global_step/sec: 72.1143
INFO:tensorflow:loss = 0.792705, step = 82501
INFO:tensorflow:global_step/sec: 70.3344
INFO:tensorflow:loss = 0.792699, step = 82601
INFO:tensorflow:global_step/sec: 68.4798
INFO:tensorflow:loss = 0.792705, step = 82701
INFO:tensorflow:global_step/sec: 73.386
INFO:tensorflow:loss = 0.792686, step = 82801
INFO:tensorflow:global_step/sec: 70.9828
INFO:tensorflow:loss = 0.792699, step = 82901
INFO:tensorflow:global_step/sec: 70.1858
INFO:tensorflow:loss = 0.792711, step = 83001
INFO:tensorflow:global_step/sec: 70.0872
INFO:tensorflow:loss = 0.792682, step = 83101
INFO:tensorflow:global_step/sec: 63.6061
INFO:tensorflow:loss = 0.792668, step = 83201
INFO:tensorflow:global_step/sec: 67.5652
INFO:tensorflow:loss = 0.792663, step = 83301
INFO:tensorflow:global_step/sec: 71.0792
INFO:tensorflow:loss = 0.792659, step = 83401
INFO:tensorflow:global_step/sec: 74.1747
INFO:tensorflow:loss = 0.792683, step = 83501
INFO:tensorflow:global_step/sec: 68.6873
INFO:tensorflow:loss = 0.792641, step = 83601
INFO:tensorflow:global_step/sec: 66.4008
INFO:tensorflow:loss = 0.792637, step = 83701
INFO:tensorflow:global_step/sec: 70.2918
INFO:tensorflow:loss = 0.79252, step = 83801
INFO:tensorflow:global_step/sec: 70.5266
INFO:tensorflow:loss = 0.792475, step = 83901
INFO:tensorflow:global_step/sec: 60.2992
INFO:tensorflow:loss = 0.792434, step = 84001
INFO:tensorflow:global_step/sec: 71.4428
INFO:tensorflow:loss = 0.792413, step = 84101
INFO:tensorflow:global_step/sec: 71.8544
INFO:tensorflow:loss = 0.792406, step = 84201
INFO:tensorflow:global_step/sec: 71.6997
INFO:tensorflow:loss = 0.792393, step = 84301
INFO:tensorflow:global_step/sec: 70.7835
INFO:tensorflow:loss = 0.792372, step = 84401
INFO:tensorflow:global_step/sec: 68.3423
INFO:tensorflow:loss = 0.792355, step = 84501
INFO:tensorflow:global_step/sec: 67.479
INFO:tensorflow:loss = 0.792351, step = 84601
INFO:tensorflow:global_step/sec: 71.7513
INFO:tensorflow:loss = 0.792346, step = 84701
INFO:tensorflow:global_step/sec: 61.0368
INFO:tensorflow:loss = 0.792324, step = 84801
INFO:tensorflow:global_step/sec: 60.8135
INFO:tensorflow:loss = 0.792326, step = 84901
INFO:tensorflow:global_step/sec: 54.1151
INFO:tensorflow:Saving checkpoints for 85000 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:Loss for final step: 0.792317.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with as_iterable is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Loading model from checkpoint: C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt-85000-?????-of-00001.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with y is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:315 in fit.: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:loss = 0.792311, step = 85001
INFO:tensorflow:Saving checkpoints for 85001 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:loss = 0.792299, step = 85101
INFO:tensorflow:global_step/sec: 47.1088
INFO:tensorflow:loss = 0.792288, step = 85201
INFO:tensorflow:global_step/sec: 50.1933
INFO:tensorflow:loss = 0.792279, step = 85301
INFO:tensorflow:global_step/sec: 53.9395
INFO:tensorflow:loss = 0.792286, step = 85401
INFO:tensorflow:global_step/sec: 54.3511
INFO:tensorflow:loss = 0.792257, step = 85501
INFO:tensorflow:global_step/sec: 68.9187
INFO:tensorflow:loss = 0.792257, step = 85601
INFO:tensorflow:global_step/sec: 68.0314
INFO:tensorflow:loss = 0.792259, step = 85701
INFO:tensorflow:global_step/sec: 65.0784
INFO:tensorflow:loss = 0.792247, step = 85801
INFO:tensorflow:global_step/sec: 72.0042
INFO:tensorflow:loss = 0.792227, step = 85901
INFO:tensorflow:global_step/sec: 69.7929
INFO:tensorflow:loss = 0.792242, step = 86001
INFO:tensorflow:global_step/sec: 68.1169
INFO:tensorflow:loss = 0.792239, step = 86101
INFO:tensorflow:global_step/sec: 65.7443
INFO:tensorflow:loss = 0.792217, step = 86201
INFO:tensorflow:global_step/sec: 72.6865
INFO:tensorflow:loss = 0.792215, step = 86301
INFO:tensorflow:global_step/sec: 71.5325
INFO:tensorflow:loss = 0.792205, step = 86401
INFO:tensorflow:global_step/sec: 72.116
INFO:tensorflow:loss = 0.79218, step = 86501
INFO:tensorflow:global_step/sec: 71.2896
INFO:tensorflow:loss = 0.792192, step = 86601
INFO:tensorflow:global_step/sec: 72.271
INFO:tensorflow:loss = 0.792194, step = 86701
INFO:tensorflow:global_step/sec: 66.9357
INFO:tensorflow:loss = 0.792176, step = 86801
INFO:tensorflow:global_step/sec: 66.1806
INFO:tensorflow:loss = 0.792159, step = 86901
INFO:tensorflow:global_step/sec: 73.4338
INFO:tensorflow:loss = 0.792167, step = 87001
INFO:tensorflow:global_step/sec: 70.0356
INFO:tensorflow:loss = 0.792169, step = 87101
INFO:tensorflow:global_step/sec: 68.6402
INFO:tensorflow:loss = 0.792157, step = 87201
INFO:tensorflow:global_step/sec: 70.1477
INFO:tensorflow:loss = 0.792158, step = 87301
INFO:tensorflow:global_step/sec: 71.3853
INFO:tensorflow:loss = 0.79213, step = 87401
INFO:tensorflow:global_step/sec: 70.1365
INFO:tensorflow:loss = 0.792136, step = 87501
INFO:tensorflow:global_step/sec: 56.7962
INFO:tensorflow:loss = 0.792142, step = 87601
INFO:tensorflow:global_step/sec: 64.4694
INFO:tensorflow:loss = 0.792137, step = 87701
INFO:tensorflow:global_step/sec: 66.7068
INFO:tensorflow:loss = 0.792128, step = 87801
INFO:tensorflow:global_step/sec: 67.8463
INFO:tensorflow:loss = 0.792112, step = 87901
INFO:tensorflow:global_step/sec: 70.9346
INFO:tensorflow:loss = 0.792113, step = 88001
INFO:tensorflow:global_step/sec: 73.6521
INFO:tensorflow:loss = 0.792103, step = 88101
INFO:tensorflow:global_step/sec: 71.0839
INFO:tensorflow:loss = 0.792109, step = 88201
INFO:tensorflow:global_step/sec: 68.2644
INFO:tensorflow:loss = 0.792087, step = 88301
INFO:tensorflow:global_step/sec: 69.8908
INFO:tensorflow:loss = 0.792082, step = 88401
INFO:tensorflow:global_step/sec: 71.137
INFO:tensorflow:loss = 0.792072, step = 88501
INFO:tensorflow:global_step/sec: 70.6333
INFO:tensorflow:loss = 0.792038, step = 88601
INFO:tensorflow:global_step/sec: 72.85
INFO:tensorflow:loss = 0.792064, step = 88701
INFO:tensorflow:global_step/sec: 73.8243
INFO:tensorflow:loss = 0.792045, step = 88801
INFO:tensorflow:global_step/sec: 70.2808
INFO:tensorflow:loss = 0.792069, step = 88901
INFO:tensorflow:global_step/sec: 63.6465
INFO:tensorflow:loss = 0.792037, step = 89001
INFO:tensorflow:global_step/sec: 66.9806
INFO:tensorflow:loss = 0.792019, step = 89101
INFO:tensorflow:global_step/sec: 70.8842
INFO:tensorflow:loss = 0.792038, step = 89201
INFO:tensorflow:global_step/sec: 71.3856
INFO:tensorflow:loss = 0.79201, step = 89301
INFO:tensorflow:global_step/sec: 71.8485
INFO:tensorflow:loss = 0.792002, step = 89401
INFO:tensorflow:global_step/sec: 71.0863
INFO:tensorflow:loss = 0.792062, step = 89501
INFO:tensorflow:global_step/sec: 70.5797
INFO:tensorflow:loss = 0.792002, step = 89601
INFO:tensorflow:global_step/sec: 66.8459
INFO:tensorflow:loss = 0.791989, step = 89701
INFO:tensorflow:global_step/sec: 71.2895
INFO:tensorflow:loss = 0.791957, step = 89801
INFO:tensorflow:global_step/sec: 72.8955
INFO:tensorflow:loss = 0.791938, step = 89901
INFO:tensorflow:global_step/sec: 69.8425
INFO:tensorflow:loss = 0.791935, step = 90001
INFO:tensorflow:global_step/sec: 66.8914
INFO:tensorflow:loss = 0.791913, step = 90101
INFO:tensorflow:global_step/sec: 68.4415
INFO:tensorflow:loss = 0.791913, step = 90201
INFO:tensorflow:global_step/sec: 70.038
INFO:tensorflow:loss = 0.79194, step = 90301
INFO:tensorflow:global_step/sec: 68.7347
INFO:tensorflow:loss = 0.791886, step = 90401
INFO:tensorflow:global_step/sec: 66.927
INFO:tensorflow:loss = 0.791863, step = 90501
INFO:tensorflow:global_step/sec: 58.9096
INFO:tensorflow:loss = 0.791855, step = 90601
INFO:tensorflow:global_step/sec: 56.5707
INFO:tensorflow:loss = 0.791845, step = 90701
INFO:tensorflow:global_step/sec: 68.4466
INFO:tensorflow:loss = 0.791848, step = 90801
INFO:tensorflow:global_step/sec: 72.4209
INFO:tensorflow:loss = 0.79183, step = 90901
INFO:tensorflow:global_step/sec: 74.371
INFO:tensorflow:loss = 0.791805, step = 91001
INFO:tensorflow:global_step/sec: 71.588
INFO:tensorflow:loss = 0.791825, step = 91101
INFO:tensorflow:global_step/sec: 73.7134
INFO:tensorflow:loss = 0.791791, step = 91201
INFO:tensorflow:global_step/sec: 73.06
INFO:tensorflow:loss = 0.791785, step = 91301
INFO:tensorflow:global_step/sec: 71.7896
INFO:tensorflow:loss = 0.791795, step = 91401
INFO:tensorflow:global_step/sec: 72.9582
INFO:tensorflow:loss = 0.791764, step = 91501
INFO:tensorflow:global_step/sec: 74.99
INFO:tensorflow:loss = 0.791776, step = 91601
INFO:tensorflow:global_step/sec: 73.2262
INFO:tensorflow:loss = 0.791751, step = 91701
INFO:tensorflow:global_step/sec: 66.1048
INFO:tensorflow:loss = 0.791738, step = 91801
INFO:tensorflow:global_step/sec: 64.0107
INFO:tensorflow:loss = 0.791737, step = 91901
INFO:tensorflow:global_step/sec: 67.4336
INFO:tensorflow:loss = 0.79173, step = 92001
INFO:tensorflow:global_step/sec: 66.979
INFO:tensorflow:loss = 0.791724, step = 92101
INFO:tensorflow:global_step/sec: 72.2729
INFO:tensorflow:loss = 0.791713, step = 92201
INFO:tensorflow:global_step/sec: 72.7032
INFO:tensorflow:loss = 0.791721, step = 92301
INFO:tensorflow:global_step/sec: 72.6863
INFO:tensorflow:loss = 0.791717, step = 92401
INFO:tensorflow:global_step/sec: 69.0603
INFO:tensorflow:loss = 0.791701, step = 92501
INFO:tensorflow:global_step/sec: 65.3565
INFO:tensorflow:loss = 0.791686, step = 92601
INFO:tensorflow:global_step/sec: 66.0491
INFO:tensorflow:loss = 0.791686, step = 92701
INFO:tensorflow:global_step/sec: 71.4876
INFO:tensorflow:loss = 0.791668, step = 92801
INFO:tensorflow:global_step/sec: 73.55
INFO:tensorflow:loss = 0.791658, step = 92901
INFO:tensorflow:global_step/sec: 73.2758
INFO:tensorflow:loss = 0.791664, step = 93001
INFO:tensorflow:global_step/sec: 67.7541
INFO:tensorflow:loss = 0.791651, step = 93101
INFO:tensorflow:global_step/sec: 72.7414
INFO:tensorflow:loss = 0.791645, step = 93201
INFO:tensorflow:global_step/sec: 72.6396
INFO:tensorflow:loss = 0.791632, step = 93301
INFO:tensorflow:global_step/sec: 73.8226
INFO:tensorflow:loss = 0.79163, step = 93401
INFO:tensorflow:global_step/sec: 71.8028
INFO:tensorflow:loss = 0.791636, step = 93501
INFO:tensorflow:global_step/sec: 68.1244
INFO:tensorflow:loss = 0.791635, step = 93601
INFO:tensorflow:global_step/sec: 74.0924
INFO:tensorflow:loss = 0.79161, step = 93701
INFO:tensorflow:global_step/sec: 72.6926
INFO:tensorflow:loss = 0.791603, step = 93801
INFO:tensorflow:global_step/sec: 68.4931
INFO:tensorflow:loss = 0.791602, step = 93901
INFO:tensorflow:global_step/sec: 72.0122
INFO:tensorflow:loss = 0.791598, step = 94001
INFO:tensorflow:global_step/sec: 64.3775
INFO:tensorflow:loss = 0.791584, step = 94101
INFO:tensorflow:global_step/sec: 62.6077
INFO:tensorflow:loss = 0.791574, step = 94201
INFO:tensorflow:global_step/sec: 70.3344
INFO:tensorflow:loss = 0.791566, step = 94301
INFO:tensorflow:global_step/sec: 72.4812
INFO:tensorflow:loss = 0.791576, step = 94401
INFO:tensorflow:global_step/sec: 72.0558
INFO:tensorflow:loss = 0.791562, step = 94501
INFO:tensorflow:global_step/sec: 71.1285
INFO:tensorflow:loss = 0.791567, step = 94601
INFO:tensorflow:global_step/sec: 73.1605
INFO:tensorflow:loss = 0.791563, step = 94701
INFO:tensorflow:global_step/sec: 73.8223
INFO:tensorflow:loss = 0.791558, step = 94801
INFO:tensorflow:global_step/sec: 65.3887
INFO:tensorflow:loss = 0.791563, step = 94901
INFO:tensorflow:global_step/sec: 72.7444
INFO:tensorflow:Saving checkpoints for 95000 into C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt.
WARNING:tensorflow:*******************************************************
WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated.
WARNING:tensorflow:Consider switching to the more efficient V2 format:
WARNING:tensorflow:   `tf.train.Saver(write_version=tf.train.SaverDef.V2)`
WARNING:tensorflow:now on by default.
WARNING:tensorflow:*******************************************************
INFO:tensorflow:Loss for final step: 0.791562.
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From C:\Users\Cheols\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dnn.py:348 in predict.: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with as_iterable is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:float64 is not supported by many models, consider casting to float32.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:fraction_of_zero_values is illegal; using dnn/hiddenlayer_0_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_0:activation is illegal; using dnn/hiddenlayer_0_activation instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:fraction_of_zero_values is illegal; using dnn/hiddenlayer_1_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/hiddenlayer_1:activation is illegal; using dnn/hiddenlayer_1_activation instead.
INFO:tensorflow:Summary name dnn/logits:fraction_of_zero_values is illegal; using dnn/logits_fraction_of_zero_values instead.
INFO:tensorflow:Summary name dnn/logits:activation is illegal; using dnn/logits_activation instead.
INFO:tensorflow:Loading model from checkpoint: C:\Users\Cheols\AppData\Local\Temp\tmparu8ecgj\model.ckpt-95000-?????-of-00001.

















In [114]:



    


#dnn_result_array.to_csv('dnn_result_array.csv')
final_prediction = []
    
for k in range(0,830):
    pp = dnn_result_array[4,k]
    final_prediction.append(pp)
        
well_data['Facies'] = final_prediction
well_data
well_data.to_csv('predict_result_dnn_Result5.csv')



    











In [112]:



    


final_prediction = []
from scipy.stats import mode
for k in range(0,830):
    pp = mode(dnn_result_array[0:multirun,k])[0][0]
    final_prediction.append(pp)
        
well_data['Facies'] = final_prediction
well_data
well_data.to_csv('predict_result_dnn_ModeResult.csv')

Post Processing





In [115]:



    


well_data["Well Name"].value_counts()
idx_s = []
idx_c = []
for i in range(len(well_data)):
    if (well_data["Well Name"].values[i] == "STUART"):
        idx_s.append(i)
    else:
        idx_c.append(i)
well_s = well_data.drop(well_data.index[idx_c])
well_c = well_data.drop(well_data.index[idx_s])



    











In [116]:



    


def smooth_results(w_data):
    data = w_data.copy()
    first_face = 0
    next_face = 0
    face_len = 0
    last_face = 0
    for i in range(len(data)):
        if(i==0):
            first_face = data["Facies"].values[i]
            continue
        next_face = data["Facies"].values[i]
        if (first_face == next_face):
            face_len = face_len+1
        if (face_len >=4):
            last_face = first_face
        if (first_face != next_face):
            if(last_face == next_face) and (face_len <4):
                for j in range(i-face_len, i):
                    data["Facies"].values[j]=last_face
                face_len = 1
            else:
                face_len = 1
                first_face = next_face
    return data



    











In [117]:



    


well_s_s = smooth_results(well_s)
well_c_s = smooth_results(well_c)



    











In [118]:



    


smooth_result = well_s_s
smooth_result = smooth_result.append(well_c_s)
smooth_result.to_csv('predict_result_dnn_full_data_smooth.csv')

Find best model by setting different parameters





In [119]:



    


def dnn_prediction(dnn,s_num):
    dnn.fit(x=X_train,y=y_train,steps=s_num)
    y_predict = []
    predictions = classifier_filtered.predict(x=X_test)

    for i, p in enumerate(predictions):
        y_predict.append(p)

    score = classifier_filtered.evaluate(x=X_test, y=y_test)["accuracy"]
    print('Accuracy: {0:f}'.format(accuracy_score))

    cv_conf = confusion_matrix(y_test, y_predict)
    return score, cv_conf

Content source: seg/2016-ml-contest

Similar notebooks:

notebook.community | gallery | about