同之前
先在此放一些大佬写好的总结吧~
转载自大佬：zhang_xinxiu -->【Machine learning（python篇)】-几种常用的数据结构
渔单渠 --> python--Numpy and Pandas 基本语法
以下是本菜鸟练习的笔记..
# <editor-fold desc="Numpy属性">
# import numpy as np
#
# array = np.array([[1, 2, 3],
# [2, 3, 4]])
# print(array)
#
# print('number of dim:', array.ndim) # 维度
# print('shape:',array.shape) # 行数 列数
# print('size:',array.size) # 元素个数
# </editor-fold>
# <editor-fold desc="Numpy创建Array">
# import numpy as np
# a = np.array([2, 23, 4], dtype=np.int) # 格式int,int32,int64,float32/54等
# print(a) # 没有逗号分隔
# print(a.dtype) # 输出格式
# a = np.array([[1, 2 ,3],
# [2, 3 ,4]])
# a0 = np.zeros((3,4)) # 生成一个全部为0的多维矩阵
# a1 = np.ones((3,4)) # 生成一个全部为1的多维矩阵
# a2 = np.arange(10, 20, 2) # 生成range数组，起始+结束+步长
# a3 = np.arange(12).reshape((3,4)) # 生成range数组，多维化
# a4 = np.linspace(1 ,10, 20).reshape((4,5)) # 生成线段，起始+结束+段数 可重新定义形状
# print(a4)
# </editor-fold>
# <editor-fold desc="Numpy基础运算1">
# import numpy as np
# a = np.array([10, 20, 30, 40])
# b = np.array([1, 2, 3, 4])
# print(a,b)
# c1 = a-b
# print(c1)
# c2 = b**2
# print(c2)
# c3 = 10*np.tan(a) # 三角函数
# print(c3)
# print(b<3) # >,< ,==,!=
# a = np.array([[10, 20],
# [20, 30]])
# b = np.array([[1, 2],
# [2, 3]])
# c = a*b # 矩阵内对应元素相乘
# c_dot = np.dot(a,b) # 矩阵乘法
# c_dot2 = a.dot(b) # 矩阵乘法第二种方式
#
# print(c)
# print(c_dot)
# print(c_dot2)
# a = np.random.random((2,4)) # 随机生成二行四列的值
# print(a)
# print(np.sum(a))
# print(np.sum(a,axis=1)) # 每一行中求和
# print(np.min(a))
# print(np.min(a,axis=0)) # 每一列中求最小值
# print(np.max(a))
# </editor-fold>
# <editor-fold desc="Numpy基础运算2">
# import numpy as np
#
# A = np.arange(2,14).reshape((3,4))
#
# print(A)
# print(np.argmin(A)) # 最小索引
# print(np.argmax(A)) # 最大索引
# print(np.mean(A)) # 平均值
# print(np.average(A)) # 平均值第二种方式
# print(np.median(A)) # 中位数
# print(np.cumsum(A)) # 前几位的累计值
# print(np.diff(A)) # 累差值
# print(np.nonzero(A)) # 非0数
# print(np.sort(A)) # 逐行排序
# print(np.transpose(A)) # 转向，行变列，列变行
# print((A.T).dot(A)) # 转向并乘
# print(np.clip(A, 5, 9)) # 小于5的变成5，大于9的变成9，5-9之间的不变
# print(np.mean(A,axis=0)) # 每一列的平均值 axis=1 每一行
# </editor-fold>
# <editor-fold desc="Numpy的索引">
# import numpy as np
#
# A = np.arange(3,15).reshape((3,4))
# print(A)
# print(A[2]) # 索引第二行
# print(A[1][1]) # 索引第一行第一列
# print(A[2,1]) # 索引第二行第一列，第二种表现方法
# print(A[:,1]) # 第一列所有数
# print(A[1,1:3]) # 第一行索引的第一个到第三个索引之间的数
# for row in A:
# print(row) # 打印每一行
# for column in A.T:
# print(column) # 通过对称-》反向 打印每一列
# print(A.flatten()) # 迭代输出
# for item in A.flat:
# print(item) # 打印每一行的数（单个值）
# </editor-fold>
# <editor-fold desc="Numpy 的Array合并">
# import numpy as np
#
# A = np.array([1, 1, 1])[:,np.newaxis]
# B = np.array([2, 2, 2])[:,np.newaxis]
#
# # C = np.vstack((A,B))
# # print(C) # 上下合并
# # print(A.shape, C.shape) # 两个序列合并成2行三列的合并
# # D = np.hstack((A,B))
# # print(D) # 左右合并
# # print(A.shape, D.shape)
#
# # 把一个横向的序列变成竖向的序列。用Tran没用
# # print(A[:,np.newaxis])
# # A = np.array([1, 1, 1])[:,np.newaxis]
#
# C = np.concatenate((A,B,B,A),axis=0) # 多个Array的合并 axis=0 纵向合并
# C1 = np.concatenate((A,B,B),axis=1) # 多个Array的合并 axis=0 横向合并
# print(C1)
# </editor-fold>
# <editor-fold desc="Numpy 的Array分割">
# import numpy as np
#
# A = np.arange(12).reshape((3,4))
# print(A)
# 只能进行等量的分割 比如4分成1，2，4部分
# print(np.split(A,2,axis=1)) # 纵向分割 分成两部分
# print(np.split(A,3,axis=0)) # 横向分割 分成三部分
# 1.使用array_split 进行不等量的分割
# print(np.array_split(A,3,axis=1))
# 2.使用v/hsplit方法 进行不等量的分割
# print(np.vsplit(A,3)) # 纵向分割成三块
# print(np.hsplit(A,2)) # 横向分割成两块
# </editor-fold>
# <editor-fold desc="Numpy的 copy 和 deepcopy">
# import numpy as np
#
# A = np.arange(4)
# print(A)
#
# # B = A # 指针传递，B就是A
# B = A.copy() # 把值传过去了 但是没有关联起来
# </editor-fold>
# <editor-fold desc="Pandas基本介绍">
# import pandas as pd
# import numpy as np
# s = pd.Series([1, 3 ,6, np.NaN,44,1])
# print(s)
# dates = pd.date_range('20181104',periods=6)
# print(dates)
# df = pd.DataFrame(np.random.randn(6,4),index=dates,columns=['a','b','c','d'])
# print(df)
# 矩阵
# df1 = pd.DataFrame(np.arange(12).reshape((3,4)))
# print(df1)
# 字典
# df2 = 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'})
# print(df2)
# print(df2.dtypes) # 查看列的格式
# print(df2.index) # 查看列的索引
# print(df2.columns) # 查看列的名字
# print(df2.values) # 查看值
# print(df2.describe()) # 运算数字形式的平均值 方差等数据
# print(df2.T) # Transport 对称
# print(df2.sort_index(axis=1, ascending=False)) # 纵向（按列），倒叙排序index
# print(df2.sort_values(by='E')) # 对'E'这一列的值进行排序
# </editor-fold>
# <editor-fold desc="Pandas 选择数据">
# import pandas as pd
# import numpy as np
#
# dates = pd.date_range('20181104',periods=6)
# df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates,columns=['A','B','C','D'])
# print(df['A'],df.A) # 选择列
# print(df[0:3],df['20181104':'20181106']) # 选择行
# select by lable: loc 纯标签
# print(df.loc['20181105']) # 根据标签选择 行
# print(df.loc[:,['A','B']]) # 选择所有行和指定列
# select by position: iloc 纯数字
# print(df.iloc[3]) # 第三行
# print(df.iloc[3,1]) # 第三行第一列
# print(df.iloc[[1,3,5],1:3]) # 选择指定行（不连续）和列
# mixed selection ix 混合上两种
# print(df.ix[:3,['A','C']])
# Bollean indexing 计算检索
# print(df[df.A>8])
# </editor-fold>
# <editor-fold desc="Pandas 设置值">
# import pandas as pd
# import numpy as np
#
# dates = pd.date_range('20181104',periods=6)
# df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates,columns=['A','B','C','D'])
# df.iloc[2,2] = 1111 # 根据索引修改值
# df.loc['20181103','B'] = 2222 # 根据标签改值
# df.B[df.A>4] = 0 # 根据条件改值
# df['F'] = np.NaN
# df['E'] = pd.Series([1,2,3,4,5,6],index=pd.date_range('20181104',periods=6))
# print(df)
# </editor-fold>
# <editor-fold desc="Pandas处理丢失数据">
# import pandas as pd
# import numpy as np
#
# dates = pd.date_range('20181104',periods=6)
# df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates,columns=['A','B','C','D'])
# df.iloc[0,1] = np.nan # 假设是丢失掉的数据
# df.iloc[1,2] = np.nan
# print(df.dropna(axis=0,how='any'))
# 丢掉行 axis=1：丢掉列
# 有任何一个就丢掉 how = 'any' how ='all' 全部为nan 才丢掉
# print(df.fillna(value=0)) # NuN值 填充为0
# print(df.isnull()) # 返回是否缺失数据
# print(np.any(df.isnull() == True)) # 返回是否缺失数据
# </editor-fold>
# <editor-fold desc="Pandas 导入导出文件">
# import pandas as pd
# import numpy as np
# data = pd.read_pickle('usrs_info.pickle')
# print(data)
# data.to_pickle('temp.pickle')
# </editor-fold>
# <editor-fold desc="Pandas 合并 concat">
# import pandas as pd
# import numpy as np
# concatennating
# <editor-fold desc="concat方法合并">
#定义资料集
# 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'])
#concat纵向合并
# res = pd.concat([df1, df2, df3], axis=0)
#打印结果
# print(res)
# a b c d
# 0 0.0 0.0 0.0 0.0
# 1 0.0 0.0 0.0 0.0
# 2 0.0 0.0 0.0 0.0
# 0 1.0 1.0 1.0 1.0
# 1 1.0 1.0 1.0 1.0
# 2 1.0 1.0 1.0 1.0
# 0 2.0 2.0 2.0 2.0
# 1 2.0 2.0 2.0 2.0
# 2 2.0 2.0 2.0 2.0
# ignore_index(重置index)
#承上一个例子，并将index_ignore设定为True
# res = pd.concat([df1, df2, df3], axis=0, ignore_index=True)
#打印结果
# print(res)
# a b c d
# 0 0.0 0.0 0.0 0.0
# 1 0.0 0.0 0.0 0.0
# 2 0.0 0.0 0.0 0.0
# 3 1.0 1.0 1.0 1.0
# 4 1.0 1.0 1.0 1.0
# 5 1.0 1.0 1.0 1.0
# 6 2.0 2.0 2.0 2.0
# 7 2.0 2.0 2.0 2.0
# 8 2.0 2.0 2.0 2.0
# </editor-fold>
# join,['inner','outer']
# <editor-fold desc="join方法合并">
#定义资料集
# df1 = pd.DataFrame(np.ones((3,4))*0, columns=['a','b','c','d'], index=[1,2,3])
# df2 = pd.DataFrame(np.ones((3,4))*1, columns=['b','c','d','e'], index=[2,3,4])
#纵向"外"合并df1与df2
# res = pd.concat([df1, df2], axis=0, join='outer')
# inner 会裁剪掉不同的地方 只保留相同的部分
# print(res)
# a b c d e
# 1 0.0 0.0 0.0 0.0 NaN
# 2 0.0 0.0 0.0 0.0 NaN
# 3 0.0 0.0 0.0 0.0 NaN
# 2 NaN 1.0 1.0 1.0 1.0
# 3 NaN 1.0 1.0 1.0 1.0
# 4 NaN 1.0 1.0 1.0 1.0
#依照`df1.index`进行横向合并， 会缺少df2的部分数据
# res = pd.concat([df1, df2], axis=1, join_axes=[df1.index])
#打印结果
# print(res)
# a b c d b c d e
# 1 0.0 0.0 0.0 0.0 NaN NaN NaN NaN
# 2 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.0
# 3 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.0
#移除join_axes，并打印结果
# res = pd.concat([df1, df2], axis=1)
# print(res)
# a b c d b c d e
# 1 0.0 0.0 0.0 0.0 NaN NaN NaN NaN
# 2 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.0
# 3 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.0
# 4 NaN NaN NaN NaN 1.0 1.0 1.0 1.0
# </editor-fold>
# append
# <editor-fold desc="append方法合并">
#定义资料集
# 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))*1, columns=['a','b','c','d'])
# s1 = pd.Series([1,2,3,4], index=['a','b','c','d'])
#将df2合并到df1的下面，以及重置index，并打印出结果
# res = df1.append(df2, ignore_index=True)
# print(res)
# a b c d
# 0 0.0 0.0 0.0 0.0
# 1 0.0 0.0 0.0 0.0
# 2 0.0 0.0 0.0 0.0
# 3 1.0 1.0 1.0 1.0
# 4 1.0 1.0 1.0 1.0
# 5 1.0 1.0 1.0 1.0
#合并多个df，将df2与df3合并至df1的下面，以及重置index，并打印出结果
# res = df1.append([df2, df3], ignore_index=True)
# print(res)
# a b c d
# 0 0.0 0.0 0.0 0.0
# 1 0.0 0.0 0.0 0.0
# 2 0.0 0.0 0.0 0.0
# 3 1.0 1.0 1.0 1.0
# 4 1.0 1.0 1.0 1.0
# 5 1.0 1.0 1.0 1.0
# 6 1.0 1.0 1.0 1.0
# 7 1.0 1.0 1.0 1.0
# 8 1.0 1.0 1.0 1.0
#合并series，将s1合并至df1，以及重置index，并打印出结果
# res = df1.append(s1, ignore_index=True)
# print(res)
# a b c d
# 0 0.0 0.0 0.0 0.0
# 1 0.0 0.0 0.0 0.0
# 2 0.0 0.0 0.0 0.0
# 3 1.0 2.0 3.0 4.0
# </editor-fold>
# </editor-fold>
# <editor-fold desc="Pandas 合并 Merge">
# merge合并 利用索引合并
# import pandas as pd
# <editor-fold desc="Merge">
#定义资料集并打印出
# 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']})
#依据key column合并，并打印出
# res = pd.merge(left, right, on='key')
#
# print(res)
# #定义资料集并打印出
# 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']})
#
# print(left)
# # A B key1 key2
# # 0 A0 B0 K0 K0
# # 1 A1 B1 K0 K1
# # 2 A2 B2 K1 K0
# # 3 A3 B3 K2 K1
#
# print(right)
# # C D key1 key2
# # 0 C0 D0 K0 K0
# # 1 C1 D1 K1 K0
# # 2 C2 D2 K1 K0
# # 3 C3 D3 K2 K0
#
# #依据key1与key2 columns进行合并，并打印出四种结果['left', 'right', 'outer', 'inner']
# res = pd.merge(left, right, on=['key1', 'key2'], how='inner')
# print(res)
# # A B key1 key2 C D
# # 0 A0 B0 K0 K0 C0 D0
# # 1 A2 B2 K1 K0 C1 D1
# # 2 A2 B2 K1 K0 C2 D2
#
# res = pd.merge(left, right, on=['key1', 'key2'], how='outer')
# print(res)
# # A B key1 key2 C D
# # 0 A0 B0 K0 K0 C0 D0
# # 1 A1 B1 K0 K1 NaN NaN
# # 2 A2 B2 K1 K0 C1 D1
# # 3 A2 B2 K1 K0 C2 D2
# # 4 A3 B3 K2 K1 NaN NaN
# # 5 NaN NaN K2 K0 C3 D3
#
# res = pd.merge(left, right, on=['key1', 'key2'], how='left')
# print(res)
# # A B key1 key2 C D
# # 0 A0 B0 K0 K0 C0 D0
# # 1 A1 B1 K0 K1 NaN NaN
# # 2 A2 B2 K1 K0 C1 D1
# # 3 A2 B2 K1 K0 C2 D2
# # 4 A3 B3 K2 K1 NaN NaN
#
# res = pd.merge(left, right, on=['key1', 'key2'], how='right')
# print(res)
# # A B key1 key2 C D
# # 0 A0 B0 K0 K0 C0 D0
# # 1 A2 B2 K1 K0 C1 D1
# # 2 A2 B2 K1 K0 C2 D2
# # 3 NaN NaN K2 K0 C3 D3
# </editor-fold>
# <editor-fold desc="indicator 显示自定义名">
# #定义资料集并打印出
# df1 = pd.DataFrame({'col1':[0,1], 'col_left':['a','b']})
# df2 = pd.DataFrame({'col1':[1,2,2],'col_right':[2,2,2]})
#
# print(df1)
# # col1 col_left
# # 0 0 a
# # 1 1 b
#
# print(df2)
# # col1 col_right
# # 0 1 2
# # 1 2 2
# # 2 2 2
#
# # 依据col1进行合并，并启用indicator=True，最后打印出
# res = pd.merge(df1, df2, on='col1', how='outer', indicator=True)
# print(res)
# # col1 col_left col_right _merge
# # 0 0.0 a NaN left_only
# # 1 1.0 b 2.0 both
# # 2 2.0 NaN 2.0 right_only
# # 3 2.0 NaN 2.0 right_only
#
# # 自定indicator column的名称，并打印出
# res = pd.merge(df1, df2, on='col1', how='outer', indicator='indicator_column')
# print(res)
# # col1 col_left col_right indicator_column
# # 0 0.0 a NaN left_only
# # 1 1.0 b 2.0 both
# # 2 2.0 NaN 2.0 right_only
# # 3 2.0 NaN 2.0 right_only
# </editor-fold>
# <editor-fold desc="Index">
# #定义资料集并打印出
# left = pd.DataFrame({'A': ['A0', 'A1', 'A2'],
# 'B': ['B0', 'B1', 'B2']},
# index=['K0', 'K1', 'K2'])
# right = pd.DataFrame({'C': ['C0', 'C2', 'C3'],
# 'D': ['D0', 'D2', 'D3']},
# index=['K0', 'K2', 'K3'])
#
# print(left)
# # A B
# # K0 A0 B0
# # K1 A1 B1
# # K2 A2 B2
#
# print(right)
# # C D
# # K0 C0 D0
# # K2 C2 D2
# # K3 C3 D3
#
# #依据左右资料集的index进行合并，how='outer',并打印出
# res = pd.merge(left, right, left_index=True, right_index=True, how='outer')
# print(res)
# # A B C D
# # K0 A0 B0 C0 D0
# # K1 A1 B1 NaN NaN
# # K2 A2 B2 C2 D2
# # K3 NaN NaN C3 D3
#
# #依据左右资料集的index进行合并，how='inner',并打印出
# res = pd.merge(left, right, left_index=True, right_index=True, how='inner')
# print(res)
# # A B C D
# # K0 A0 B0 C0 D0
# # K2 A2 B2 C2 D2
# </editor-fold>
# <editor-fold desc="解决overlapping的问题">
# #定义资料集
# boys = pd.DataFrame({'k': ['K0', 'K1', 'K2'], 'age': [1, 2, 3]})
# girls = pd.DataFrame({'k': ['K0', 'K0', 'K3'], 'age': [4, 5, 6]})
#
# #使用suffixes解决overlapping的问题
# res = pd.merge(boys, girls, on='k', suffixes=['_boy', '_girl'], how='inner')
# print(res)
# # age_boy k age_girl
# # 0 1 K0 4
# # 1 1 K0 5
# </editor-fold>
# </editor-fold>
# <editor-fold desc="Pandas plot 画图">
# import pandas as pd
# import numpy as np
# import matplotlib.pyplot as plt
#
# # plot data
#
# # Series # 线性
# # data = pd.Series(np.random.randn(1000),index=np.arange(1000))
# # data = data.cumsum() # 累加
# # data.plot()
# # plt.show()
#
# # DataFrame # 数据点
# data = pd.DataFrame(np.random.randn(1000,4),index=np.arange(1000),columns=list('ABCD')) # randn(1000,4)4个属性
# data = data.cumsum()
# # data.plot() # 有很多参数可以设置
# # plot methods:
# # 'bar','hist','box','kde','area','scatter','hexbin','pie'
# ax = data.plot.scatter(x='A' ,y='B',color='DarkBlue',label='Class 1')
# data.plot.scatter(x='A',y='C',color='DarkGreen',label='Class 2',ax=ax)
# plt.show()
# </editor-fold>
扫一扫
3万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
