def submit(test_df, h1n1_clf, seasonal_clf):
test_df = clean_data(test_df)
X_test = test_df.iloc[:, 1:]
test_ids = test_df.iloc[:, 0]
# X_test, test_ids = X_test.astype(str), test_ids.astype(int)
X_test = X_test.astype('category')
h1n1_preds = h1n1_clf.predict(X_test)
seasonal_preds = seasonal_clf.predict(X_test)
result_df = concat([test_ids,
DataFrame(h1n1_preds, columns=['h1n1_vaccine']),
DataFrame(seasonal_preds, columns=['seasonal_vaccine'])],
axis=1)
# print(f'Exporting as pickle...')
# dump(model, open("classifier.pkl", "wb"))
result_df.to_csv('Submissions/submission.csv', index=False)
print('done')
result_df = concat([test_ids,
DataFrame(h1n1_preds, columns=['h1n1_vaccine']),
DataFrame(seasonal_preds, columns=['seasonal_vaccine'])],
axis=1)
# print(f'Exporting as pickle...')
# dump(model, open("classifier.pkl", "wb"))
result_df.to_csv('Submissions/submission.csv', index=False)
print('done')
def classify(document):
model = pickle.load(
open("model.pkl", "rb")
) #using pickled clf model (will be most recent version if retrained)
vectorizer = pickle.load(
open("vectorizer.pkl", "rb")
) #using pickled vectorizer object (will be most recent verion if retrained)
label_dict = {0: 'non_satire', 1: 'satire'}
cleandocument = clean_data(document)
X = vectorizer.transform([cleandocument])
y = model.predict(X)[0]
proba = np.max(model.predict_proba(X))
return label_dict[y], proba, cleandocument
def preprocess_data(df, count):
if 'id' in df.columns:
df = df.drop(['id'], axis=1)
if 'stroke' in df.columns:
df = df.drop(['stroke'], axis=1)
df = clean_data(df)
df = one_hot_encode(df, colnames=['work_type', 'smoking_status'])
df = normalize_columns(df,
colnames=['avg_glucose_level', 'bmi'],
scaler=MinMaxScaler())
df = df.iloc[:count, :]
# print(list(df.columns))
return df
def submit(test_df, model):
test_df = clean_data(test_df)
X_test = test_df.iloc[:, 1:]
test_ids = test_df.iloc[:, 0]
X_test = np.array(X_test)
X_test, test_ids = X_test.astype(str), test_ids.astype(int)
h1n1_preds, seasonal_preds = make_predictions(model, X_test)
result_df = concat([test_ids,
DataFrame(h1n1_preds, columns=['h1n1_vaccine']),
DataFrame(seasonal_preds, columns=['seasonal_vaccine'])],
axis=1)
print(f'Exporting as pickle...')
dump(model, open("classifier.pkl", "wb"))
result_df.to_csv('Submissions/submission.csv', index=False)
print('done')
def submit(test_df, model):
test_df = clean_data(test_df)
ohe_cols = cols[1:36]
test_df = one_hot_encode(test_df, colnames=ohe_cols)
X_test = test_df.iloc[:, 1:]
test_ids = test_df.iloc[:, 0]
X_test = np.array(X_test)
h1n1_preds, seasonal_preds = make_predictions(model, X_test)
result_df = concat([
test_ids,
DataFrame(h1n1_preds, columns=['h1n1_vaccine']),
DataFrame(seasonal_preds, columns=['seasonal_vaccine'])
],
axis=1)
print(f'Exporting as pickle...')
# dump(model, open("classifier.pkl", "wb"))
model.save('nn_model')
print('neural network pickled')
result_df.to_csv('Submissions/submission.csv', index=False)
print('done')
, cat_features=cat_features
, random_state=42,
verbose=30
))
ovr.fit(x_train, y_train)
cross_validated = np.mean(cross_val_score(ovr, x_train, y_train, cv=5))
print(f'Cross Validation Score: {cross_validated}')
return ovr
if __name__ == '__main__':
df = import_data(train=True)
test_df = import_data(features='Datasets/test_set_features.csv', train=False)
cols = list(df.columns)
set_df_values(df)
df = clean_data(df)
x_train, x_val, y_train, y_val, train_ids, val_ids = split_dataset(df, test_size=0.1, seed=42)
x_train, y_train = x_train.astype(str), y_train.astype(int)
x_val, y_val = x_val.astype(str), y_val.astype(int)
# model = fit_random_search_model(x_train, y_train)
model = fit_model(x_train, y_train)
h1n1_preds, seasonal_preds = make_predictions(model, x_train)
h1n1_true, seasonal_true = y_train['h1n1_vaccine'].values.tolist(), y_train['seasonal_vaccine'].values.tolist()
train_score = get_scores(h1n1_true, h1n1_preds, seasonal_true, seasonal_preds)
print(f'Training Accuracy: {train_score}')
h1n1_preds, seasonal_preds = make_predictions(model, x_val)
h1n1_true, seasonal_true = y_val['h1n1_vaccine'].values.tolist(), y_val['seasonal_vaccine'].values.tolist()
validation_score = get_scores(h1n1_true, h1n1_preds, seasonal_true, seasonal_preds)
print(f'Validation Accuracy: {validation_score}')