Account Clean

clean.py

# Function to open and clean
def clean(file_raw, month):
    # Open the file and start from line 5
    df_raw = pd.read_excel(file_raw, header = 5)
    df_raw.head()

    # Remove First Lines
    df_clean = df_raw.copy()
    df_clean = df_clean.iloc[4:]

    # FillNa with '-' (strings)
    for col in df_raw.columns[0:2]:
        df_clean[col] = df_clean[col].fillna('-')

    # FillNa with 0 (numeric)
    for col in df_raw.columns[2:]:
        df_clean[col] = df_clean[col].fillna(0).round(1)

    # TRIM Column values 
    df_clean.columns = [str(t).strip() for t in df_clean.columns]

    return df_clean