def test_get(tcp_db_connection):
main.create_tables()
context = main.get_index_context()
assert isinstance(context, dict)
assert len(context.get("recent_votes")) >= 0
assert context.get("tab_count") >= 0
assert context.get("space_count") >= 0
def setUp(self):
app = create_app("settings.TestingConfig")
self.db = create_db(app)
create_resources(app)
self.app = app.test_client()
with app.app_context():
create_tables()
from main import create_tables create_tables()
import main main.create_tables() main.create_fixture()
#!/usr/bin/env python import main main.create_tables() main.app.run()
plt.ylabel('True Positive Rate')
plt.title(f'DNN model- {name}\nMax accuracy={round(max(accuracy),2)}, learning rate={lr}, epochs={epochs}')
plt.legend(loc="lower right")
plt.savefig('Log_ROC')
# plt.show()
# plt.savefig(f'/home/michal/MYOR Dropbox/R&D/Allergies Product Development/Prediction/Algorithm_Beta/18_01_2021_CARE_results/{name}-statistics-DNN.jpeg')
# plt.show()
# plt.savefig(f'/home/michal/MYOR Dropbox/R&D/Allergies Product Development/Prediction/Algorithm_Beta/18_01_2021_CARE_results/{name}-statistics-randomForest.jpeg')
# plt.savefig('Log_ROC')
if __name__ == '__main__':
FA, label, name=Type('AD')
merged_df=create_tables(run_tables_creation=False,FA=FA)
y =merged_df[label]
X = merged_df.drop(columns=[label])
X_train, X_test, y_train, y_test = train_test_split(X, np.where(y > 0, 1, 0), test_size=0.1, stratify=np.where(y > 0, 1, 0))
CARE_df=CARE_data()
print(CARE_df.shape)
CARE_df=CARE_df[X_train.columns]
Random_forest_regress(X_train, X_test, y_train, y_test,CARE_df,n_estimators=200, name=name)
DNN_regress(X_train, X_test, y_train, y_test,CARE_df, epochs=200, lr=0.0001,name=name)
FA, label, name=Type('FA')
merged_df=create_tables(run_tables_creation=False,FA=FA)
