Pandas处理DataFrame稀疏数据及维度不匹配数据分析详解_python

def deal_defect(df,n):
    df_defect=df.iloc[:,n:]
    m=4
    list_columns=[]
    for i in range(df_defect.shape[1]):
        list_columns.append('features%d'%m)
        m=m+1
    df_defect.columns=list_columns
    df_all=pd.concat([df.iloc[:,:n],df_defect],axis=1)
    return df_all
deal_defect(df,5)

df_fill=df.astype('int')

IntCastingNaNError: Cannot convert non-finite values (NA or inf) to integer

def fill_conver(df):
    df_fill=df.astype('float')
    df_fill=abs(df_fill)
    df_fill=df_fill.fillna('')
    df_fill=df_fill.replace('',-1)
    df_fill=df_fill.astype(int)
    return df_fill
fill_conver(df)

def get_features(df):
    list_all_link=[]
    df=df.iloc[:,2:]
    for i in range(df.shape[0]):
        #flag为控制外层循环开关
        flag=1
        for j in range(df.shape[1]):
            if(flag==0):
                break
            if(j%2==0):
                if(df.iloc[i:i+1,j].item()==-1):
                    flag=0
                else:
                    list_all_link.append(list(df.iloc[i:i+1,j]))
    return list_all_link
get_features(df)

def unique_df(df):
    df_features=df.iloc[:,2:]
    unique_series=pd.Series(pd.Series(df_features.iloc[:,[i%2==0 for i in range(len(df_features.columns))]].values.ravel()).unique())
    list_series=list(unique_series.values)
    return list_series
unique_list=unique_df(df)
unique_list.remove(-1)
unique_list