pandas---综合练习

注：本博客跟随此Pandas教程进行学习，有兴趣可以学习一下。

df = pd.read_csv('Data/Game_of_Thrones_Script.csv')
print(df)
df['Name'].nunique()
df['Name'].value_counts().index[0]
df_words = df.assign(Words=df['Sentence'].apply(lambda x:len(x.split()))).sort_values(by='Name')
print(df_words)
L_count = []
N_words = list(zip(df_words['Name'],df_words['Words']))
for i in N_words:
    if i == N_words[0]:
        L_count.append(i[1])
        last = i[0]
    else:
        L_count.append(L_count[-1]+i[1] if i[0]==last else i[1])
        last = i[0]
df_words['Count']=L_count
df_words['Name'][df_words['Count'].idxmax()]
df = pd.read_csv('data/Kobe_data.csv',index_col='shot_id')
print(df)
pd.Series(list(zip(df['action_type'],df['combined_shot_type']))).value_counts().index[0]
pd.Series(list(list(zip(*(pd.Series(list(zip(df['game_id'],df['opponent'])))
                          .unique()).tolist()))[1])).value_counts().index[0]
df = pd.read_csv('data/UFO.csv')
df.rename(columns={'duration (seconds)':'duration'},inplace=True)
df['duration'].astype('float')
print(df)
df.query('duration > 60')['shape'].value_counts().index[0]

bins_long = np.linspace(-180,180,13).tolist()
bins_la = np.linspace(-90,90,11).tolist()
cuts_long = pd.cut(df['longitude'],bins=bins_long)
df['cuts_long'] = cuts_long
cuts_la = pd.cut(df['latitude'],bins=bins_la)
df['cuts_la'] = cuts_la
print(df)
df = pd.read_csv('data/Pokemon.csv')
print(df)
attribute = df.query('Legendary == True')[['Type 1','Total']].set_index('Type 1')
max_value = 0
result = ''
for i in attribute.index.unique():
    temp = float(attribute.loc[i,:].mean())
    if temp > max_value:
        max_value = temp
        result = i
result
df = pd.read_csv('data/Diamonds.csv')
print(df)