def main_deprecated():
# This is deprecated, never use this please.
print("This is main, alhumdulliah")
##### This block is for data cleaning #####
missing_values = ["n/a", "na", "--", "?"]
raw_data = pd.read_csv('../dataset_diabetes/diabetic_data.csv',
delimiter=',', na_values=missing_values)
# print(raw_data.head()) # print head of the data
# print(raw_data.describe()) # shows numerical columns statistics e.g. count, mean, std, min, max etc
# print(raw_data.shape) # prints shape of the dataset (101766, 50)
# print(raw_data["weight"].isnull().sum()) #prints number of null values in weight column
# print(raw_data["weight"].shape[0]) #prints number of columns in weight column
data_cleaning = DataCleaning()
raw_data = data_cleaning.clean_columns(raw_data, missing_bound=.2)
cols_having_missing_values = data_cleaning.get_cols_having_missing_values(
raw_data, False) # cols having missing values
# raw_data.dtypes #shows the column data types
raw_data = data_cleaning.fill_missing_values(
raw_data, cols_having_missing_values)
# print(get_cols_having_missing_values(raw_data, False)) #no columns with missing values
raw_data = data_cleaning.just_remove_columns(raw_data, columns=[
"encounter_id", "patient_nbr", "admission_type_id", "discharge_disposition_id", "admission_source_id", "num_procedures"])
df = raw_data
my_util = Util()
my_util.save_df(df, "../only_calculated_datasets/cleaned_df.pkl")
print("Filled the missing values either by the mode or mean value")
def clean():
missing_values = ["n/a", "na", "--", "?"]
raw_data = pd.read_csv('../dataset_diabetes/diabetic_data.csv',
delimiter=',', na_values=missing_values)
data_cleaning = DataCleaning()
raw_data = data_cleaning.clean_columns(raw_data, missing_bound=.2)
cols_having_missing_values = data_cleaning.get_cols_having_missing_values(
raw_data, False) # cols having missing values
raw_data = data_cleaning.fill_missing_values(
raw_data, cols_having_missing_values)
raw_data = data_cleaning.just_remove_columns(raw_data, columns=[
"encounter_id", "patient_nbr", "admission_type_id", "discharge_disposition_id", "admission_source_id", "num_procedures"])
df = raw_data
my_util = Util()
my_util.save_df(df, "../only_calculated_datasets/cleaned_df.pkl")