Created
June 26, 2023 07:42
-
-
Save doutv/04c02a26194af0aab274b1a7890bd3f5 to your computer and use it in GitHub Desktop.
SeeDAO翻译公会:翻译库归档->统计贡献榜
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# %% | |
import pandas as pd | |
df = pd.read_csv('db.csv') | |
# print(df.head()) | |
print(df.columns) | |
# %% | |
df = df[["翻译","校对","信源","状态"]] | |
# remove trailing spaces from all columns | |
df = df.applymap(lambda x: x.strip() if isinstance(x, str) else x) | |
# %% | |
xinyuan = df[~df["状态"].isin([""])]["信源"].drop_duplicates() | |
fanyi = df[~df["状态"].isin(["待翻译", "翻译中", ""])]["翻译"].drop_duplicates() | |
jiaodui = df[~df["状态"].isin(["待翻译", "翻译中", "", "待校对", "校对中"])]["校对"].drop_duplicates() | |
users = pd.concat([xinyuan, fanyi, jiaodui], axis=0) | |
users = pd.unique(users) | |
new_df = pd.DataFrame({"成员":users}) | |
print(new_df) | |
# %% | |
for col in ['信源', '翻译', '校对']: | |
for index, row in new_df.iterrows(): | |
user = row['成员'] | |
count = (df[col] == user).sum() | |
new_df.at[index, col] = count | |
print(new_df.head()) | |
new_df.to_csv('contribution.csv', index=False, encoding='utf-8') | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment