Python笔记 #16# Pandas: Operations

10 Minutes to pandas

 

#Stats

# shift 这玩意儿有啥用？？？
s = pd.Series([1,5,np.nan], index=dates).shift(0)
# s1 = pd.Series([1,5,np.nan], index=dates).shift(1)
# s2 = pd.Series([1,5,np.nan], index=dates).shift(2)
# print(s)
# print(s1)
# print(s2)
# 2018-01-16    1.0
# 2018-01-17    5.0
# 2018-01-18    NaN
# Freq: D, dtype: float64
# 2018-01-16    NaN
# 2018-01-17    1.0
# 2018-01-18    5.0
# Freq: D, dtype: float64
# 2018-01-16    NaN
# 2018-01-17    NaN
# 2018-01-18    1.0
# Freq: D, dtype: float64

# print(df)
# print(df.sub(s, axis='index')) # "Wise subtraction"
#                    A         B         C         D
# 2018-01-16 -1.809723  0.342129  2.048727  0.995959
# 2018-01-17  0.871955  1.960730  0.368855  0.459528
# 2018-01-18 -0.483717  0.031247  0.619609 -0.712104
#                    A         B         C         D
# 2018-01-16 -2.809723 -0.657871  1.048727 -0.004041
# 2018-01-17 -4.128045 -3.039270 -4.631145 -4.540472
# 2018-01-18       NaN       NaN       NaN       NaN

 /

# Applying functions to the data
# print(df)
# print(df.apply(np.cumsum)) # 应用 numpy 的函数 cumsum 对每列累计求和
#                    A         B         C         D
# 2018-01-16  1.516139  0.501701  0.624571 -1.270804
# 2018-01-17 -0.223673 -0.092153  0.782620 -2.073206
# 2018-01-18  0.844318 -1.180269  0.994821 -1.372318
#                    A         B         C         D
# 2018-01-16  1.516139  0.501701  0.624571 -1.270804
# 2018-01-17  1.292466  0.409548  1.407191 -3.344010
# 2018-01-18  2.136784 -0.770721  2.402013 -4.716328

/

# Histogramming（直方图化） ps：就是把每个值出现的次数统计出来
# s = pd.Series(np.random.randint(0, 7, size=10))
# print(s)
# print(s.value_counts())
# 0    1
# 1    4
# 2    6
# 3    2
# 4    4
# 5    2
# 6    3
# 7    2
# 8    1
# 9    5
# dtype: int32
# 2    3
# 4    2
# 1    2
# 6    1
# 5    1
# 3    1
# dtype: int64

/

# String Methods
# s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])
# print(s.str.lower())
# 0       a
# 1       b
# 2       c
# 3    aaba
# 4    baca
# 5     NaN
# 6    caba
# 7     dog
# 8     cat
# dtype: object