import tensorflow as tf
import pandas as pd
import models
print 'Reading evaluation data...'
eval_df = pd.read_csv('data/merged_eval_2016_total.csv',
parse_dates=['transactiondate'])
models.fillna_df(eval_df)
eval_df = models.add_outlier_column(eval_df)
eval_df = models.add_sign_column(eval_df)
model = models.logsign_classifier
results = model.evaluate(input_fn=lambda: models.input_fn(eval_df, 'logsign'),
steps=1)
# results = model.evaluate(input_fn=lambda: models.input_fn(eval_df_outl), steps=1)
# results2 = model.evaluate(input_fn=lambda: models.input_fn(eval_df), steps=1)
print 'Results:'
print results
print model.get_variable_names()
# models.print_dnn(model)
# print 'Logits:'
# for weight in model.get_variable_value('dnn/logits/weights').flatten():
# print ' {: .3f}x + {: .3f}'.format(weight, model.get_variable_value('dnn/logits/biases')[0])
# print model.get_variable_value('dnn/hiddenlayer_0/weights')
# print model.get_variable_value('dnn/hiddenlayer_0/biases')
input_samples = eval_df.sample(n=20)
import tensorflow as tf
import pandas as pd
import numpy as np
import models
tf.logging.set_verbosity(tf.logging.ERROR)
print 'Reading training data...'
train_df = pd.read_csv('data/merged_train_2016_total.csv',
parse_dates=['transactiondate'])
models.fillna_df(train_df)
err_std = train_df['logerror'].std()
err_mean = train_df['logerror'].mean()
query_outl = '(logerror >= ' + str(
err_std + err_mean) + ') or (logerror <= ' + str(err_mean - err_std) + ')'
query_norm = '(logerror < ' + str(
err_std + err_mean) + ') or (logerror > ' + str(err_mean - err_std) + ')'
train_df_outl = train_df.query(query_outl)
train_df_norm = train_df.query(query_norm)
#feature_columns = [
# tf.contrib.layers.real_valued_column('taxamount', dtype=tf.float64),
# tf.contrib.layers.real_valued_column('yearbuilt', dtype=tf.float64)
#]
model = models.dnn_regressor
print 'Training...'
for _ in range(1):
print 'Iteration: %f' % (_ + 1)
model.fit(input_fn=lambda: models.input_fn(train_df_outl), steps=50000)