import pandas as pd
import numpy as np

pd.Series([1, 3, 6, np.nan, 44, 1]) # np.nan 相当于 None

dates = pd.date_range('20160101', periods=6)
dates

pd.DataFrame(np.random.randn(6, 4), index=dates, columns=['a', 'b', 'c', 'd'])

pd.DataFrame(np.arange(12).reshape((3, 4)))

df = pd.DataFrame({'A': 1,
                   'B': pd.Timestamp('20130102'),
                   'C': pd.Series(1, index=list(range(4)), dtype='float32'),
                   'D': np.array([3] * 4, dtype='int32'),
                   'E': pd.Categorical(["test", "train", "test", "train"]),
                   'F': 'foo'})
df

df.dtypes

df.index

df.columns

df.values

df.describe()

df.T

df.sort_index(axis=1, ascending=False) # 以行排序，倒序

df.sort_index(axis=0, ascending=False)

df.sort_values(by='E')

import pandas as pd
import numpy as np
 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6, 4)), index=dates, columns=['A', 'B', 'C', 'D'])
df

df.A

df['A']

df[0:3]

df['20130102':'20130104']

df.loc['20130102']

df.loc[:, ['A', 'B']]

df.loc['20130102', ['A', 'B']]

df.iloc[3]

df.iloc[3, 1]

df.iloc[3:5, 1:3]

df.iloc[[1, 3, 5], 1:3]

df.ix[:3, ['A', 'C']] # 高版本中已不推荐使用

df[df.A > 8] # 只对比 A，但是 ABCD 都会显示

import pandas as pd
import numpy as np
 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6, 4)), index=dates, columns=['A', 'B', 'C', 'D'])

dates

df

df.iloc[2, 2] = 1111
df.loc['20130101', 'B'] = 2222
df[df.A > 4] = 0
df.B[df.A > 4] = 0
df

df['F'] = np.nan
df

df['E'] = pd.Series([1, 2, 3, 4, 5, 6], index=pd.date_range('20130101', periods=6))
df

import pandas as pd
import numpy as np
 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6, 4)), index=dates, columns=['A', 'B', 'C', 'D'])
df.iloc[0, 1] = np.nan
df.iloc[1, 2] = np.nan
df

df.dropna(axis=0, how='any') # how = {'any', 'all'} 出现 nan/所有数据都是 nan 是才处理

df.fillna(value=0)

df.isna()

df.isnull()

np.any(df.isnull() is True) # 若返回 True，则说明表格中的确缺失数据

import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
 
fig = plt.figure()  # 新建一个 figure 窗口
ax = Axes3D(fig, auto_add_to_figure=False)  # 添加三维坐标轴
fig.add_axes(ax)
 
# 输入数据
X = np.arange(-4, 4, 0.25)
Y = np.arange(-4, 4, 0.25)
X, Y = np.meshgrid(X, Y)
R = np.sqrt(X ** 2 + Y ** 2)
Z = np.sin(R)
 
ax.plot_surface(X, Y, Z, rstride=1, cstride=1, cmap=plt.get_cmap('rainbow'))
ax.contourf(X, Y, Z, zdir='z', offset=-2, cmap='rainbow')
ax.set_zlim(-2, 2)
 
plt.show()

import pandas as pd 
import numpy as np

df1 = pd.DataFrame(np.ones((3, 4)) * 0, columns=['a', 'b', 'c', 'd'])
df2 = pd.DataFrame(np.ones((3, 4)) * 1, columns=['a', 'b', 'c', 'd'])
df3 = pd.DataFrame(np.ones((3, 4)) * 2, columns=['a', 'b', 'c', 'd'])

df1

df2

df3

pd.concat([df1, df2, df3], axis=0) # axis=0 竖向划分操作行，1 横向划分操作列

pd.concat([df1, df2, df3], axis=0, ignore_index=True) # 重新排序索引

df1 = pd.DataFrame(np.ones((3, 4)) * 0, columns=['a', 'b', 'c', 'd'])
df2 = pd.DataFrame(np.ones((3, 4)) * 1, columns=['b', 'c', 'd', 'e'])
df1

df2

pd.concat([df1, df2], join='outer')

pd.concat([df1, df2], join='inner') # 只会合并相同的部分

pd.concat([df1, df2], join='inner', ignore_index=True)

pd.concat([df1, df2], axis=1, join_axes=[df1.index])

df1.append([df2, df3])

import pandas as pd
 
left = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
                     'A':   ['A0', 'A1', 'A2', 'A3'],
                     'B':   ['B0', 'B1', 'B2', 'B3']})
right = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
                      'C':   ['C0', 'C1', 'C2', 'C3'],
                      'D':   ['D0', 'D1', 'D2', 'D3']})

left

right

pd.merge(left, right, on='key')

left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
                     'key2': ['K0', 'K1', 'K0', 'K1'],
                     'A':   ['A0', 'A1', 'A2', 'A3'],
                     'B':   ['B0', 'B1', 'B2', 'B3']})
right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
                      'key2': ['K0', 'K0', 'K0', 'K0'],
                      'C':   ['C0', 'C1', 'C2', 'C3'],
                      'D':   ['D0', 'D1', 'D2', 'D3']})
left

right

pd.merge(left, right, on=['key1', 'key2'], how='inner')

pd.merge(left, right, on=['key1', 'key2'], how='outer')

pd.merge(left, right, on=['key1', 'key2'], how='left')

pd.merge(left, right, on=['key1', 'key2'], how='right', indicator=True) # indicator 显示合并的方式

pd.merge(left, right, on=['key1', 'key2'], how='right', indicator="indicator_column") # indicator 显示合并的方式

pd.merge(left, right, left_index=True, right_index=True, how='outer')

boys = pd.DataFrame({'k': ['K0', 'K1', 'K2'], 'age': [1, 2, 3]})
girls = pd.DataFrame({'k': ['K0', 'K1', 'K2'], 'age': [4, 5, 6]})
boys

girls

pd.merge(boys, girls, on='k', suffixes=['_boy', '_girl'], how='inner')

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

data = pd.Series(np.random.randn(1000), index=np.arange(1000)).cumsum()
data

data.plot()
plt.show()

data = pd.DataFrame(np.random.randn(1000, 4), index=np.arange(1000), columns=list('ABCD')).cumsum()
data

data.plot()
plt.show()

ax = data.plot.scatter(x='A', y='B', color='DarkBlue', label='Class1')
data.plot.scatter(x='A', y='C', color='DarkGreen', label='Class2', ax=ax)
plt.show()