ndarray、series和dataframe类型转化

创建ndarray类型数据

• 使用numpy库中的np.array创建

## 创建ndarray类型数据
import numpy as np
data = [["2017-10-18", 10.53, 10.69, 10.70, 10.51, 871365.0],
        ["2017-10-19", 10.64, 10.63, 10.72, 10.57, 722764.0],
        ["2017-10-20", 10.59, 10.48, 10.59, 10.41, 461808.0],
        ["2017-10-23", 10.39, 10.19, 10.40, 10.15, 1074465.0]]
arr_1 = np.array(data)
print(arr_1)
print(type(arr_1))#

• 结果
  

使用list创建series

• 使用pandas库构建series, index构造series的行索引

import numpy as np
import pandas as pd
data = [["2017-10-18", 10.53, 10.69, 10.70, 10.51, 871365.0],
        ["2017-10-19", 10.64, 10.63, 10.72, 10.57, 722764.0],
        ["2017-10-20", 10.59, 10.48, 10.59, 10.41, 461808.0],
        ["2017-10-23", 10.39, 10.19, 10.40, 10.15, 1074465.0]]

series = pd.Series(data, index=['a', 'b', 'c', 'd'])
print(series)
print(type(series))#

• 结果

series和ndarray转化

• 使用变量名.values实现转化
• 使用变量名.as_matrix()会报错AttributeError: ‘Series’ object has no attribute ‘as_matrix’

arr = series.values
print(arr)
print(type(arr))#

• 结果
  

使用list创建dataframe

• 使用pandas库构建dataframe,index和columns构造dataframe的行列索引

import pandas as pd
data = [["2017-10-18", 10.53, 10.69, 10.70, 10.51, 871365.0],
        ["2017-10-19", 10.64, 10.63, 10.72, 10.57, 722764.0],
        ["2017-10-20", 10.59, 10.48, 10.59, 10.41, 461808.0],
        ["2017-10-23", 10.39, 10.19, 10.40, 10.15, 1074465.0]]

df = pd.DataFrame(data, index=["2017-10-18", "2017-10-19", "2017-10-20", "2017-10-23"],
                  columns=['date',"open", "close", "high", "low", "volume"])

print(df)
print(type(df))

• 结果
  

dataframe和ndarray之间的转化

• 使用变量名.values实现转化

arr_1 = df.values
print(arr_1)
print(type(arr_1))#

• 结果
  

dataframe和series之间的转化

• dataframe取子列得到series

series_open = df["open"]
print(series_open)
print(type(series_open))#

• 结果
  

• 完整代码

##
import numpy as np
import pandas as pd
data = [["2017-10-18", 10.53, 10.69, 10.70, 10.51, 871365.0],
        ["2017-10-19", 10.64, 10.63, 10.72, 10.57, 722764.0],
        ["2017-10-20", 10.59, 10.48, 10.59, 10.41, 461808.0],
        ["2017-10-23", 10.39, 10.19, 10.40, 10.15, 1074465.0]]

series = pd.Series(data, index=['a', 'b', 'c', 'd'])
print(series)
print(type(series))#
#arr = series.as_matrix()：报错AttributeError: 'Series' object has no attribute 'as_matrix'
#series和ndarray的转化
arr = series.values
print(arr)
print(type(arr))#


## dataframe
import pandas as pd
data = [["2017-10-18", 10.53, 10.69, 10.70, 10.51, 871365.0],
        ["2017-10-19", 10.64, 10.63, 10.72, 10.57, 722764.0],
        ["2017-10-20", 10.59, 10.48, 10.59, 10.41, 461808.0],
        ["2017-10-23", 10.39, 10.19, 10.40, 10.15, 1074465.0]]

df = pd.DataFrame(data, index=["2017-10-18", "2017-10-19", "2017-10-20", "2017-10-23"],
                  columns=['date',"open", "close", "high", "low", "volume"])

print(df)
print(type(df))
#arr = series.as_matrix()：报错AttributeError: 'Series' object has no attribute 'as_matrix'
#dataframe和ndarray的转化
arr_1 = df.values
print(arr_1)
print(type(arr_1))#




## dataframe和series之间的转化：dataframe取子列得到series
series_open = df["open"]
print(series_open)
print(type(series_open))#


## 创建ndarray类型数据
import numpy as np
data = [["2017-10-18", 10.53, 10.69, 10.70, 10.51, 871365.0],
        ["2017-10-19", 10.64, 10.63, 10.72, 10.57, 722764.0],
        ["2017-10-20", 10.59, 10.48, 10.59, 10.41, 461808.0],
        ["2017-10-23", 10.39, 10.19, 10.40, 10.15, 1074465.0]]
arr_1 = np.array(data)
print(arr_1)
print(type(arr_1))#