def create_data(input_dir, file_names, output_dir, dtype, threadid):
name_lst = []
i = 0
sz = len(file_names)
for f in file_names:
print("Importing data {}/{} for {} in thread {}...".format(i, sz, dtype, threadid))
i += 1
loc = os.path.join(input_dir, f + '.txt')
out = os.path.join(input_dir, f + '.npy')
import_data(loc, None, out)
name_lst.append(out)
# merge_n_split(name_lst, output_dir)
merge(name_lst, output_dir, dtype, threadid)
def create_data(input_dir, file_names, output_dir, dtype, threadid,
class_type):
name_lst = []
i = 0
sz = len(file_names)
for f in file_names:
print("Importing data {}/{} for {} in thread {}...".format(
i, sz, dtype, threadid))
i += 1
dset_id = f
loc = os.path.join(
input_dir,
dset_id + '.txt') #from 'formated folder'; i.e. formated txt file
out = os.path.join(input_dir, dset_id + '.npy')
import_data(loc, None, out, class_type)
name_lst.append(out)
merge(name_lst, output_dir, dtype, threadid, class_type)
print('"merge" is finished!')
elif i == 1:
resp_list.append('The person is at risk of heart stroke.')
else:
print(f'somethings wrong, i is {i}')
else:
print(
'something is wrong in input. Contact administrator at [email protected]'
)
resp_df = DataFrame(resp_list, columns=['Prediction'])
st.subheader('Prediction')
st.dataframe(resp_df)
set_theme(style="white")
train_df = import_data(train=True)
corr = train_df.corr()
# Generate a mask for the upper triangle
mask = np.triu(np.ones_like(corr, dtype=bool))
# Set up the matplotlib figure
f, ax = plt.subplots(figsize=(3, 3))
# Generate a custom diverging colormap
cmap = diverging_palette(256, 20, as_cmap=True)
res = heatmap(
corr,
vmax=1,
square=True,
cmap="YlGnBu",
linewidths=0.1,
annot=True,
, learning_rate=0.05
, eval_metric='AUC'
, random_strength=6
, 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}')
def run_import():
main()
import_data()
