def plot_feature_importances_this(X_train, Y_repeater, Y_numRepeats, Y_quantiles, num_features):
"""
@param num_features: number of features for [repeater, numrepeats, quantiles]
"""
fields_repeater = plot_feature_importances(np.array(X_train), Y_repeater, labels=X_train.columns, numTopFeatures=num_features[0], title='Repeater')[1]
fields_numRepeats = plot_feature_importances(np.array(X_train), Y_numRepeats, labels=X_train.columns, numTopFeatures=num_features[1], title='Number of Repeats')[1]
fields_quantiles = plot_feature_importances(np.array(X_train), Y_quantiles, labels=X_train.columns, numTopFeatures=num_features[2], title='Quantiles of Number of Repeats')[1]
return fields_repeater, fields_numRepeats, fields_quantiles
if __name__ == '__main__':
x_train, y_train, _, columns_train, weights, y_class = \
process_data('/home/jj/code/Kaggle/Fire/Data/train.csv',
impute=True, imputeDataDir='/home/jj/code/Kaggle/Fire/intermediateOutput', imputeStrategy='median',
fieldsToUse=['var11', 'var8', 'var13'])
# fieldsToUse=FIELDS_CLASS_GBC_TOP100[:30])
# fieldsToUse=FIELDS_CDF_CORR_TOP99[:19])
# y_cdfs = np.array(pandas.read_csv('/home/jj/code/Kaggle/Fire/Data/y_pcdfs.csv')).reshape(NUM_TRAIN_SAMPLES,)[:len(y_train)] # in case smallTrain is used
# clf = GradientBoostingRegressor(loss='quantile', learning_rate=0.02, n_estimators=100, subsample=0.9)
# clf = LogisticRegression()
plot_feature_importances(x_train, np.array(y_train), columns_train, numTopFeatures=3, numEstimators=50)
classifier = SVR(kernel='rbf')
regressor = Ridge(alpha=1)
classFields = fieldNamesToInd(columns_train, FIELDS_CLASS_GBC_TOP100[:20])
regFields = fieldNamesToInd(columns_train, FIELDS_CORR_ORDERED_TOP99[:20])
# clf = GroupThenRegress(list(columns_train).index('var8'),
# Ridge(alpha=1, normalize=False),
# verbose=1)
# clf = SVR()
# ================== CORRELATION ==================
# print '================== CORRELATION =================='
# print x_train.shape