print("Positive and negative movement in test data outcome.") print(y_test.value_counts()) dp.apply_logistic_regressor(X_train, y_train, X_test, y_test) dp.apply_svc(X_train, y_train, X_test, y_test) dp.apply_knn(X_train, y_train, X_test, y_test) dp.apply_random_forest(X_train, y_train, X_test, y_test) parameters = {'kernel': ('linear', 'rbf'), 'C': [1, 10, 100, 1000]} bp=dp.select_best_param_svc(X_train, y_train, parameters) dp.apply_svc(X_train, y_train, X_test, y_test, kernel='rbf', C=1) dp.apply_svc(X_train, y_train, X_test, y_test, kernel='linear', C=1) symbol = 'CNX-NIFTY' bars = d.fetch_data_from_yahoo('^NSEI', start_test, end_date) X_train, y_train, X_test, y_test = dp.partition_data(merged_data, len(bars)) predict_svc = dp.get_svc_prediction(X_train, y_train, X_test, kernel=bp['kernel'], C=bp['C']) signals_svc = pd.DataFrame(index=bars.index) signals_svc['signal'] = 0.0 signals_svc['signal'] = predict_svc signals_svc['positions'] = signals_svc['signal'].diff() portfolio_svc = MarketIntradayPortfolio(symbol, bars, signals_svc) returns_svc = portfolio_svc.backtest_portfolio() predict_rf = dp.get_randomforest_prediction(X_train, y_train, X_test, 50) signals_rf = pd.DataFrame(index=bars.index) signals_rf['signal'] = 0.0