第二章 pandas基础（参考答案）

In [29]: df = pd.read_csv('data/pokemon.csv')
In [30]: (df[['HP', 'Attack', 'Defense', 'Sp. Atk', 'Sp. Def', 'Speed'
   ....:    ]].sum(1)!=df['Total']).mean()
   ....: 
Out[30]: 0.0

In [31]: dp_dup = df.drop_duplicates('#', keep='first')
In [32]: dp_dup['Type 1'].nunique()
Out[32]: 18
In [33]: dp_dup['Type 1'].value_counts().index[:3]
Out[33]: Index(['Water', 'Normal', 'Grass'], dtype='object')

In [34]: attr_dup = dp_dup.drop_duplicates(['Type 1', 'Type 2'])
In [35]: attr_dup.shape[0]
Out[35]: 143

In [36]: L_full = [i+' '+j if i!=j else i for i in df['Type 1'
   ....:          ].unique() for j in df['Type 1'].unique()]
   ....: 
In [37]: L_part = [i+' '+j if not isinstance(j, float) else i for i, j in zip(
   ....:           df['Type 1'], df['Type 2'])]
   ....: 
In [38]: res = set(L_full).difference(set(L_part))
In [39]: len(res) # 太多，不打印了
Out[39]: 170

In [40]: df['Attack'].mask(df['Attack']>120, 'high'
   ....:                  ).mask(df['Attack']<50, 'low').mask((50<=df['Attack']
   ....:                  )&(df['Attack']<=120), 'mid').head()
   ....: 
Out[40]: 
0    low
1    mid
2    mid
3    mid
4    mid
Name: Attack, dtype: object

In [41]: df['Type 1'].replace({i:str.upper(i) for i in df['Type 1'
   ....:             ].unique()}).head()
   ....: 
Out[41]: 
0    GRASS
1    GRASS
2    GRASS
3    GRASS
4     FIRE
Name: Type 1, dtype: object
In [42]: df['Type 1'].apply(lambda x:str.upper(x)).head()
Out[42]: 
0    GRASS
1    GRASS
2    GRASS
3    GRASS
4     FIRE
Name: Type 1, dtype: object

In [43]: df['Deviation'] = df[['HP', 'Attack', 'Defense', 'Sp. Atk',
   ....:                      'Sp. Def', 'Speed']].apply(lambda x:np.max(
   ....:                      (x-x.median()).abs()), 1)
   ....: 
In [44]: df.sort_values('Deviation', ascending=False).head()
Out[44]: 
       #                 Name  Type 1  Type 2  Total   HP  Attack  Defense  Sp. Atk  Sp. Def  Speed  Deviation
230  213              Shuckle     Bug    Rock    505   20      10      230       10      230      5      215.0
121  113              Chansey  Normal     NaN    450  250       5        5       35      105     50      207.5
261  242              Blissey  Normal     NaN    540  255      10       10       75      135     55      190.0
333  306    AggronMega Aggron   Steel     NaN    630   70     140      230       60       80     50      155.0
224  208  SteelixMega Steelix   Steel  Ground    610   75     125      230       55       95     30      145.0

In [45]: np.random.seed(0)
In [46]: s = pd.Series(np.random.randint(-1,2,30).cumsum())
In [47]: s.ewm(alpha=0.2).mean().head()
Out[47]: 
0   -1.000000
1   -1.000000
2   -1.409836
3   -1.609756
4   -1.725845
dtype: float64
In [48]: def ewm_func(x, alpha=0.2):
   ....:     win = (1-alpha)**np.arange(x.shape[0])[::-1]
   ....:     res = (win*x).sum()/win.sum()
   ....:     return res
   ....: 
In [49]: s.expanding().apply(ewm_func).head()
Out[49]: 
0   -1.000000
1   -1.000000
2   -1.409836
3   -1.609756
4   -1.725845
dtype: float64

In [50]: s.rolling(window=4).apply(ewm_func).head() # 无需对原函数改动
Out[50]: 
0         NaN
1         NaN
2         NaN
3   -1.609756
4   -1.826558
dtype: float64