Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 16 additions & 12 deletions homework/m2_pandas_cleaning.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,26 +19,23 @@ def green_read_csv():
讀取 orders_raw.csv,回傳原始 DataFrame(不做任何清理)
提示:pd.read_csv()
"""
# TODO: 你的程式碼
pass
return pd.read_csv("datasets/ecommerce/orders_raw.csv")


def green_shape(df):
"""
回傳 DataFrame 的 (列數, 欄數) tuple
提示:df.shape
"""
# TODO: 你的程式碼
pass
return df.shape


def green_dtypes(df):
"""
回傳 DataFrame 的欄位型別 (Series)
提示:df.dtypes
"""
# TODO: 你的程式碼
pass
return df.dtypes


# ============================================================
Expand All @@ -51,8 +48,9 @@ def yellow_clean_columns(df):
回傳清理後的 DataFrame(不要修改原始 df)
提示:df.columns.str.strip().str.lower()
"""
# TODO: 你的程式碼
pass
new_df = df.copy()
new_df.columns = new_df.columns.str.strip().str.lower()
return new_df


def yellow_clean_amount(df):
Expand All @@ -62,17 +60,23 @@ def yellow_clean_amount(df):
回傳清理後的 DataFrame(不要修改原始 df)
提示:.str.replace() + .astype(float)
"""
# TODO: 你的程式碼
pass
new_df = df.copy()
new_df['amount'] = (
new_df['amount']
.astype(str)
.str.replace('$', '', regex=False)
.str.replace(',', '', regex=False)
.astype(float)
)
return new_df


def yellow_drop_duplicates(df):
"""
移除完全重複的列,回傳去重後的 DataFrame
提示:df.drop_duplicates()
"""
# TODO: 你的程式碼
pass
return df.drop_duplicates()


# ============================================================
Expand Down
Loading