def prepare_fly(Fmonth, Dmonth1, Dmonth2, year, period, instType='spread'):
Fmonth, Fmonth_n, Fmonth_d = load_data(Fmonth, year, interval='1min')
Fmonth = resamplePeriod(Fmonth, period=period)
Dmonth1, Dmonth_n1, Dmonth_d1 = load_data(Dmonth1, year, interval='1min')
Dmonth1 = resamplePeriod(Dmonth1, period=period)
Dmonth2, Dmonth_n2, Dmonth_d2 = load_data(Dmonth2, year, interval='1min')
Dmonth2 = resamplePeriod(Dmonth2, period=period)
x = Fmonth.loc[Fmonth.index.intersection(Dmonth1.index.values), :].dropna()
y = Dmonth1.loc[Dmonth1.index.intersection(x.index.values), :]
z = Dmonth2.loc[Dmonth2.index.intersection(x.index.values), :].dropna()
x = x.loc[x.index.intersection(z.index.values), :].dropna()
y = y.loc[y.index.intersection(z.index.values), :].dropna()
s1 = (x - y).Close
s2 = (y - z).Close
if instType == 'spread':
return s1, s2
if instType == 'fly':
return (s1 - s2).dropna()
from DataProcessing import load_data
from DataProcessing import split_data
from DataProcessing import encode_class_labels
from DataProcessing import report_results
from DataProcessing import extract_feats_from_text
from DataProcessing import extract_feats_from_text_and_desc
from sklearn.model_selection import GridSearchCV
from sklearn.naive_bayes import MultinomialNB
JOBS = 4
PARAMS = [{'alpha': [8, 4, 2, 1, 0.5, 0.25, 0.1, 0.07, 0.05, 0.03, 0.01, 0.001]}]
df = load_data()
x_train, x_test , index_train1, index_test1 = split_data()
y_train, class_names = encode_class_labels(x_train)
y_test, class_names1 = encode_class_labels(x_test)
print("Features only from Text")
X_train, X_test = extract_feats_from_text()
grid_search = GridSearchCV(MultinomialNB(), PARAMS, n_jobs=JOBS, verbose=5, cv=4,
scoring="f1")
grid_search.fit(X_train, y_train)
report_results(grid_search, y_train, X_train, y_test, X_test, class_names)
from sklearn.model_selection import GridSearchCV
import matplotlib.pyplot as plt
import seaborn as sns
plt.rc("font", size=14)
sns.set(style="white")
sns.set(style="whitegrid", color_codes=True)
PARAMS = [{
'penalty': ["l1", "l2"],
'C': [4, 2, 1.5, 1, 0.5, 0.1, 0.05, 0.01, 0.001, 0.0001]
}]
JOBS = 4
data = load_data()
# print(list(data.columns))
x_train, x_test, index_train1, index_test1 = split_data()
# print(data.shape)
# print(x_test.shape)
# print(x_train.shape)
# array = ['male', 'female']
# data1 = x_test.loc[:, 'gender'].values
# data2 = x_train.loc[:, 'gender'].values
y_train, class_names_train = encode_class_labels(x_train)
y_test, class_names_test = encode_class_labels(x_test)
# print(len(data1))
cross_validator = CrossVal(X, y, 10, model)
cross_validator.fit()
test_mse = np.mean(cross_validator.test_mses)
train_mse = np.mean(cross_validator.train_mses)
results.append([p, train_mse, test_mse])
return pd.DataFrame(results,
columns=['polynomials', 'train_mse', 'test_mse'])
if __name__ == "__main__":
print("\n### OLS ### \n")
X, y = load_data()
model = OLS()
# Running trials for different polynomials
results = test_diffent_polynomials(X, y)
results.to_csv(cfg.RESULT_FOLDER.joinpath('OLS_polynomial_results.csv'))
best_poly = results[results.test_mse ==
results.test_mse.min()].polynomials.tolist()[0]
model_summary(model, add_polynomials(X, best_poly), y)
bias_variance_plot(results.polynomials,
results.train_mse,
results.test_mse,
save=True)