1. data增加一列
import pandas as pd
import numpy as np
filepath = "back.csv"
#读取文件到train,类型为dataframe
train = pd.read_csv(filepath)
#均是列名
target = 'ptype'
IDcol = 'id'
#计算有多少行
sum = train[target].value_counts()
#创建一个值为0的ndarray 长度为sum
tmp =np.zeros(sum,dtype=np.int32)
#参数分别是 1纵轴索引,2新增列名,3数据data(长度要求与原列数相同)
train.insert(25,'label',tmp)
print(train)
保存文件
train.to_csv(filepath)
2.合并两个dataframe
import pandas as pd
import numpy as np
df1 =pd.DataFrame(np.arange(10).reshape(2,5))
df2 =pd.DataFrame(np.arange(20).reshape(4,5))
print(df1)
print(df2)
#将df2添加到df1后边,存入result, ignore_index表示改变df2的行索引值设为df1的行索引值之后
result = df1.append(df2,ignore_index=True)
print(result)
五行代码合并两个.csv文件
import pandas as pd
train = pd.read_csv("back.csv")
neris = pd.read_csv("neris.csv")
result = train.append(neris,ignore_index=True)
result.to_csv("backaneris.csv")