df_train, df_test = data.load_data(cache=True)
df = data.create_fulldf(df_train, df_test)
df = df.fillna(NULL_VALUE)
df = data.clean_data(df)
df = data.encode_labels(df)
#df = features.add_features(df)
logerror = df['logerror'].values
targets = logerror
df = data.select_features(df)
df = df.drop(['assessmentyear'], axis=1)
print df.columns
if cv_flag:
df_full_train, targets, df_test = data.split_data(df, logerror)
df_train, df_val, train_targets, val_targets = data.split_cv(df_full_train, targets, cv_split_ratio)
cv_preds = np.repeat(0., len(df_val))
for i in range(n_bags):
x_train, x_val = tools.normalise_data(df_train.values, df_val.values)
model = model_params.get_keras(x_train.shape[1])
history = model.fit(
x_train, train_targets,
nb_epoch=epochs, batch_size=batch_size,
validation_data=(x_val, val_targets), verbose=2)
model.history = history
cv_preds += model.predict(x_val).squeeze()
cv_preds /= float(n_bags)
mae = tools.get_mae_loss(val_targets, cv_preds)
return predictions
def predict_multiple_months(df_test, predict_func):
sub = pd.read_csv('../input/sample_submission.csv')
df = df_test.copy()
for c in sub.columns[sub.columns != 'ParcelId']:
df['transaction_month'] = np.repeat(c[4:6], len(df))
df['transaction_year'] = np.repeat(c[0:4], len(df))
predictions = predict_func(model, df.values)
print 'predicting for ' + c + ' ' + str(predictions.sum())
sub[c] = predictions
return sub
if __name__ == '__main__':
df_train, df_test = data.load_data()
1/0
df = data.create_fulldf(df_train, df_test)
df = df.fillna(NULL_VALUE)
df = data.clean_data(df)
df = data.encode_labels(df)
df = features.add_features(df)
#df = data.add_month_and_year(df)
targets = df['logerror'].values
df = data.select_features(df)
df_train, targets, df_test = data.split_data(df, targets)
model = train_xgb_cv(df_train, targets)
sub = predict_multiple_months(df_test, predict_xgb)
data.generate_kaggle_file(sub, 'sub/xgb_try_exper_quasi.csv')
