from scipy.stats import chi2 from scipy.stats import entropy import numpy as np from collections import Counter import math from petfinder.get_explore import read_data, Columns from petfinder.preprocessing import prepare_data from petfinder.feature_engineering import finalize_data, add_features, filter_by_varth from petfinder.tools import detect_outliers, plog if __name__ == "__main__": sys.stdout.buffer.write(chr(9986).encode('utf8')) pd.set_option('display.max_columns', 500) pd.set_option('display.width', 1000) train, test = read_data() train, test = prepare_data(train, test) train, test = add_features(train, test) ccols = train.columns.values.tolist() for c in ccols: if (train[c].isna().any()) & \ (c in Columns.img_num_cols_1.value + Columns.img_num_cols_2.value + Columns.img_num_cols_3.value ): plog("filling " + c + " with 0 on train dataset") train[c].fillna(0, inplace=True) ccols = test.columns.values.tolist() for c in ccols: if (test[c].isna().any()) & \ (c in Columns.img_num_cols_1.value + Columns.img_num_cols_2.value + Columns.img_num_cols_3.value ): plog("filling " + c + " with 0 on test dataset") test[c].fillna(0, inplace=True)
from mord import OrdinalRidge from petfinder.get_explore import read_data from petfinder.preprocessing import prepare_data import pandas as pd if __name__ == "__main__": train, test = read_data() x_train, y_train, x_test, id_test = prepare_data(train, test) clf = OrdinalRidge() clf.fit(x_train, y_train) pred = clf.predict(x_test) print(clf.score(x_train, y_train)) print(pd.DataFrame({'PetID': id_test.PetID.values.ravel(), 'AdoptionSpeed': pred}))
'PetID': test_id.values.ravel(), 'AdoptionSpeed': pred }) return prediction_df if __name__ == "__main__": pd.set_option('display.max_columns', 500) pd.set_option('display.width', 1500) df = pd.DataFrame(np.random.randn(5, 3), columns=['perf', 'B', 'C']) #predict(df) train, test = read_data() train_x, train_y, test_x, test_id = prepare_data(train, test) #rs = randomsearchpipeline(train_x.drop(["RescuerID"], axis=1), train_y) train_x.drop(["RescuerID"], axis=1, inplace=True) test_x.drop(["RescuerID"], axis=1, inplace=True) #print(train_x) #print(rs) #sys.exit() #print(train_x) #print(train_y) #print(sp.stats.randint(1, 6).value) clf, mean = iterate_by_randomsearch(train_x, train_y.values.ravel()) print(clf) print(mean) #for c in clf[""]: #print(c)