python全棧闖關--pandas

一、導入

import pandas as pd
import numpy as np

二、數據結構

一、Series

s = pd.Series([1, 2, 3, 4, 5, np.nan, 6, 7])
print(s)
# 0    1.0
# 1    2.0
# 2    3.0
# 3    4.0
# 4    5.0
# 5    NaN
# 6    6.0
# 7    7.0
# dtype: float64

二、DataFrame

dates = pd.date_range('20190101', periods=6)
# index行名，columns列名
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=['a', 'b', 'c', 'd'])
print('列選取'.center(50, '-'))
print(df)
#                    a         b         c         d
# 2019-01-01 -1.294464  0.706790 -0.164825 -0.237432
# 2019-01-02 -1.091822  0.824446  0.748465 -0.191267
# 2019-01-03 -0.755218  1.637604 -1.896371 -0.093815
# 2019-01-04 -2.610031 -0.705783 -1.247235 -1.398978
# 2019-01-05 -0.324550  1.014212  1.375527 -0.409117
# 2019-01-06 -0.512911  0.301417  1.227190  0.771551

# 按照列選擇
print('列選取'.center(50, '-'))
print(df['c'])
# 2019-01-01   -0.164825
# 2019-01-02    0.748465
# 2019-01-03   -1.896371
# 2019-01-04   -1.247235
# 2019-01-05    1.375527
# 2019-01-06    1.227190
# Freq: D, Name: c, dtype: float64

 

三、建立特定數據的DataFrame

df_1 = pd.DataFrame({
    'A': 1,  # 直接賦值，若是index數量大於1，默認此列按照這個值重複
    'B': pd.Timestamp('20190930'),  # 直接賦值Timestamp格式，多行，重複這個值
    'C': pd.Series(2, index=list(range(4)), dtype='float'),  # Series結構使用index，定義出整個函數的值
    'D': pd.Categorical([1, 2, 3, 4]),
    'E': ['a', 'b', 'c', 'd'],
    'F': 'beer',
    'G': [1, 5, 4, 4]
})
print(df_1)
#    A          B    C  D  E     F  G
# 0  1 2019-09-30  2.0  1  a  beer  1
# 1  1 2019-09-30  2.0  2  b  beer  5
# 2  1 2019-09-30  2.0  3  c  beer  4
# 3  1 2019-09-30  2.0  4  d  beer  4

 

四、DataFrame經常使用屬性及排序

print('types'.center(50, '-'))
print(df_1.dtypes)  # 按列列出每列的數據類型
# A             int64
# B    datetime64[ns]
# C           float64
# D          category
# E            object
# F            object
# G             int64
# dtype: object

print('index'.center(50, '-'))
print(df_1.index, type(df_1.index))  # Int64Index([0, 1, 2, 3], dtype='int64')
# Int64Index([0, 1, 2, 3], dtype='int64') <class 'pandas.core.indexes.numeric.Int64Index'>

print('columns'.center(50, '-'))
print(df_1.columns, type(df_1.columns))  # Index(['A', 'B', 'C', 'D', 'E', 'F'], dtype='object')
# Index(['A', 'B', 'C', 'D', 'E', 'F', 'G'], dtype='object') <class 'pandas.core.indexes.base.Index'>

print('values'.center(50, '-'))
print(df_1.values, type(df_1.values))  # 打印值，結果未numpy結構
# [[1 Timestamp('2019-09-30 00:00:00') 2.0 1 'a' 'beer' 1]
#  [1 Timestamp('2019-09-30 00:00:00') 2.0 2 'b' 'beer' 5]
#  [1 Timestamp('2019-09-30 00:00:00') 2.0 3 'c' 'beer' 4]
#  [1 Timestamp('2019-09-30 00:00:00') 2.0 4 'd' 'beer' 4]] <class 'numpy.ndarray'>


print('describe'.center(50, '-'))
print(df_1.describe())  # 打印值，結果爲numpy結構
#          A    C         G
# count  4.0  4.0  4.000000  計數
# mean   1.0  2.0  2.500000  平均數
# std    0.0  0.0  1.290994  方差
# min    1.0  2.0  1.000000  最小值
# 25%    1.0  2.0  1.750000  第一分位數
# 50%    1.0  2.0  2.500000  第二分位數
# 75%    1.0  2.0  3.250000  第三分位數
# max    1.0  2.0  4.000000  最大值

print('數據翻轉'.center(50, '-'))
print(df_1.T)  # 打印值，結果未numpy結構
#                0  ...                    3
# # A                    1  ...                    1
# # B  2019-09-30 00:00:00  ...  2019-09-30 00:00:00
# # C                    2  ...                    2
# # D                    1  ...                    4
# # E                    a  ...                    d
# # F                 beer  ...                 beer
# # G                    1  ...                    4
#
# [7 rows x 4 columns]

print('數據按照列排序'.center(50, '-'))
# axis=1,按照行進行排序
# axis=0,按照列進行排序
# ascending=False倒序輸出，True爲正序輸出
print('按照index排序'.center(50, '-'))
print(df_1.sort_index(axis=0, ascending=False))
#    A          B    C  D  E     F  G
# 3  1 2019-09-30  2.0  4  d  beer  4
# 2  1 2019-09-30  2.0  3  c  beer  4
# 1  1 2019-09-30  2.0  2  b  beer  5
# 0  1 2019-09-30  2.0  1  a  beer  1

print('G列排序'.center(50, '-'))
print(df_1.sort_values(by='G', ascending=False))  # 按照一列值排序
#    A          B    C  D  E     F  G
# 1  1 2019-09-30  2.0  2  b  beer  5
# 2  1 2019-09-30  2.0  3  c  beer  4
# 3  1 2019-09-30  2.0  4  d  beer  4
# 0  1 2019-09-30  2.0  1  a  beer  1

print('G，D列排序'.center(50, '-'))
print(df_1.sort_values(by=['G', 'D'], ascending=False))  # 按照多列值排序
#    A          B    C  D  E     F  G
# 1  1 2019-09-30  2.0  2  b  beer  5
# 3  1 2019-09-30  2.0  4  d  beer  4
# 2  1 2019-09-30  2.0  3  c  beer  4
# 0  1 2019-09-30  2.0  1  a  beer  1

print('數據按照行排序'.center(50, '-'))
index = list(range(4))
col = ['A', 'B', "C", 'D', 'E']
d_sort = pd.DataFrame(np.arange(20).reshape(4, 5), index=index, columns=col)
# print(d_sort)
print(d_sort.sort_values(by=[1, 2], axis=1, ascending=False))  # 按照行值排序
#     E   D   C   B   A
# 0   4   3   2   1   0
# 1   9   8   7   6   5
# 2  14  13  12  11  10
# 3  19  18  17  16  15

五、選擇數據

index = ['A', 'B', "C", 'D', 'E']
dates = pd.date_range('20191001', periods=10)
df = pd.DataFrame(np.random.randn(10, 5), index=dates, columns=index)
# print(df)
print('選擇某列'.center(50, '-'))
print(df['A'])
# 2019-10-01   -0.595401
# 2019-10-02    1.264714
# 2019-10-03    1.179423
# 2019-10-04   -0.516471
# 2019-10-05    0.891850
# 2019-10-06   -0.011205
# 2019-10-07   -0.206089
# 2019-10-08    0.972745
# 2019-10-09   -0.135309
# 2019-10-10    1.590818
# Freq: D, Name: A, dtype: float64

print('切片選擇'.center(50, '-'))
print(df[0:3])  # 按照行數切片
print(df['2019-10-02':'2019-10-05'])  # 按照索引值進行切片
#              A         B         C         D         E
# 2019-10-01 -0.595401  0.337930  0.034220  1.472752 -0.555414
# 2019-10-02  1.264714  0.518856 -1.148349  1.674159 -0.473919
# 2019-10-03  1.179423  2.036095 -0.719042  1.607909  2.659472
#                    A         B         C         D         E
# 2019-10-02  1.264714  0.518856 -1.148349  1.674159 -0.473919
# 2019-10-03  1.179423  2.036095 -0.719042  1.607909  2.659472
# 2019-10-04 -0.516471  1.733509 -0.177231  0.260795 -0.106666
# 2019-10-05  0.891850  0.665301  0.013627 -1.346193  0.222099

# 按照行切片[0:3]值切片到了0-2行
# 按照值'2019-10-02':'2019-10-05'切片，切到完整的日期範圍

print('按照行精確選擇'.center(50, '-'))
print(df.loc['2019-10-02', ['A', 'B']])  # 按照行精確選擇列
# A    1.264714
# B    0.518856
# Name: 2019-10-02 00:00:00, dtype: float64

print('行號選擇數據'.center(50, '-'))
print(df.iloc[3, 1])
# 1.7335085248615345
# 行數從0開始計數


print(df.iloc[3:5, 0:2])  # 輸出4到到5行的數據，1到2列的數據
#                    A         B
# 2019-10-04 -0.516471  1.733509
# 2019-10-05  0.891850  0.665301
# 切片從0開始計數，顧頭部顧尾

print('混合選擇'.center(50, '-'))
print(df.ix[0:3, ['B', 'C']])
#                    B         C
# 2019-10-01  0.337930  0.034220
# 2019-10-02  0.518856 -1.148349
# 2019-10-03  2.036095 -0.719042


print('條件選擇'.center(50, '-'))
print(df[df.A > 0])
#                    A         B         C         D         E
# 2019-10-01  0.391314  0.647378  0.065032 -0.436882 -0.482698
# 2019-10-02  1.742555  0.374014  0.737914  1.708461  0.328336
# 2019-10-03  0.024506 -0.455824 -0.397145  1.523103  1.361226
# 2019-10-04  0.140041 -0.604164 -0.397656 -0.423711 -0.626598
# 2019-10-05  0.027898  0.159293 -1.000558  0.921370 -1.613052
# 2019-10-08  1.411249 -1.292006  0.140944  0.699647 -0.065080
# 2019-10-10  0.306495  0.590515 -0.524972  0.521179 -0.805736