「無法將float Nan轉換爲int」但不是Nan？

Question

我有一個數據幀，並試圖進行以下操作：

data['SD_rates']=np.array([int((data['actual value'][i]-data['means'][i])/data['std'][i]) for i in range (len(data['means']))]) 

它與下面的消息打破： 「無法轉換浮動楠爲int」

這是一個錯誤我理解，但用data.isnull（）測試了df，沒有涉及的列包括NaN（我通過發送data.to_csv手動控制它）。

我甚至用fillna（-1，inplace = True）填充數據['std']，但仍然中斷。我不明白爲什麼，因爲沒有除0（我也控制這個列中沒有零，所以沒有原始的0和Null/Nan填充-1），實際值和手段是fillna（0 ）的缺失值，無論如何，減法不能產生一個nan（數據範圍[0-10]）。

什麼可能是錯的？ （正如我所說的，觸發操作之前的數據是正確的...）。由於

---

下面的代碼片段：
我的一個假設是，在某些方面，GROUPBY可能產生NaN的，在計算我的手段時，我無法擺脫掉（但我認爲，這是被熊貓自動忽略......）並且沒有填充0或-1（我故意選擇-1作爲標準偏差以避免被0除）。

def stats_setting(data): 

    print('Stats settings') 
    print(data.columns) 
    print(data.dtypes) 
    #sys.exit() 

    data['marks']=np.log1p(data['marks'].astype(float)) 
    data['students']=np.log1p(data['students'].astype(float))#Rossman9 think this has to be tested 
    #were filled with fillna before) 

#First Part: by studentType and Assortment 
    types_DoM_select=['Type','Type2','Category'] 

#First Block:types_DoM students grouped by categories 
#wonder if can do a groupby of groupb 
    print("types_DoM_marks_means") 
    types_DoM_marks_means = data.groupby(types_DoM_select)['marks'].mean() 
    types_DoM_marks_means.name = 'types_DoM_marks_means' 
    types_DoM_marks_means = types_DoM_marks_means.reset_index() 
    data = pd.merge(data, types_DoM_marks_means, on = types_DoM_select, how='left') 

    print("types_DoM_students_means") 
    types_DoM_students_means = data.groupby(types_DoM_select)['students'].mean() #.students won't work. Why? 
    types_DoM_students_means.name = 'types_DoM_students_means' 
    types_DoM_students_means=types_DoM_students_means.reset_index()  
    data = pd.merge(data, types_DoM_students_means, on = types_DoM_select, how='left') 

    print("types_DoM_marks_medians") 
    types_DoM_marks_medians = data.groupby(types_DoM_select)['marks'].median() 
    types_DoM_marks_medians.name = 'types_DoM_marks_medians' 
    types_DoM_marks_medians = types_DoM_marks_medians.reset_index() 
    data = pd.merge(data, types_DoM_marks_medians, on = types_DoM_select, how='left') 

    print("types_DoM_students_medians") 
    types_DoM_students_medians = data.groupby(types_DoM_select)['students'].median() #.students won't work. Why? 
    types_DoM_students_medians.name = 'types_DoM_students_medians' 
    types_DoM_students_medians=types_DoM_students_medians.reset_index()  
    data = pd.merge(data, types_DoM_students_medians, on = types_DoM_select, how='left') 
    print("types_DoM_marks_std") 
    types_DoM_marks_std = data.groupby(types_DoM_select)['marks'].std() 
    types_DoM_marks_std.name = 'types_DoM_marks_std' 
    types_DoM_marks_std = types_DoM_marks_std.reset_index() 
    data = pd.merge(data, types_DoM_marks_std, on = types_DoM_select, how='left') 


    print("types_DoM_students_std") 
    types_DoM_students_std = data.groupby(types_DoM_select)['students'].std() 
    types_DoM_students_std.name = 'types_DoM_students_std' 
    types_DoM_students_std = types_DoM_students_std.reset_index() 
    data = pd.merge(data, types_DoM_students_std, on = types_DoM_select, how='left') 

    data['types_DoM_marks_means'].fillna(-1, inplace=True) 
    data['types_DoM_students_means'].fillna(-1, inplace=True) 
    data['types_DoM_marks_medians'].fillna(-1, inplace=True) 
    data['types_DoM_students_medians'].fillna(-1, inplace=True) 
    data['types_DoM_marks_std'].fillna(-1, inplace=True) 
    data['types_DoM_students_std'].fillna(-1, inplace=True) 

#Second Part: by specific student 
    student_DoM_select=['Type','Type2','Category'] 

#First Block:student_DoM 
#wonder if can do a groupby of groupb 
    print("student_DoM_marks_means") 
    student_DoM_marks_means = data.groupby(student_DoM_select)['marks'].mean() 
    student_DoM_marks_means.name = 'student_DoM_marks_means' 
    student_DoM_marks_means = student_DoM_marks_means.reset_index() 
    data = pd.merge(data, student_DoM_marks_means, on = student_DoM_select, how='left') 

    print("student_DoM_students_means") 
    student_DoM_students_means = data.groupby(student_DoM_select)['students'].mean() #.students won't work. Why? 
    student_DoM_students_means.name = 'student_DoM_students_means' 
    student_DoM_students_means=student_DoM_students_means.reset_index()  
    data = pd.merge(data, student_DoM_students_means, on = student_DoM_select, how='left') 

    print("student_DoM_marks_medians") 
    student_DoM_marks_medians = data.groupby(student_DoM_select)['marks'].median() 
    student_DoM_marks_medians.name = 'student_DoM_marks_medians' 
    student_DoM_marks_medians = student_DoM_marks_medians.reset_index() 
    data = pd.merge(data, student_DoM_marks_medians, on = student_DoM_select, how='left') 

    print("student_DoM_students_medians") 
    student_DoM_students_medians = data.groupby(student_DoM_select)['students'].median() #.students won't work. Why? 
    student_DoM_students_medians.name = 'student_DoM_students_medians' 
    student_DoM_students_medians=student_DoM_students_medians.reset_index()  
    data = pd.merge(data, student_DoM_students_medians, on = student_DoM_select, how='left') 

    # May I use data['marks','students','marksMean','studentsMean','marksMedian','studentsMedian']=data['marks','students','marksMean','studentsMean','marksMedian','studentsMedian'].astype(int) to spare memory? 

    print("student_DoM_marks_std") 
    student_DoM_marks_std = data.groupby(student_DoM_select)['marks'].std() 
    student_DoM_marks_std.name = 'student_DoM_marks_std' 
    student_DoM_marks_std = student_DoM_marks_std.reset_index() 
    data = pd.merge(data, student_DoM_marks_std, on = student_DoM_select, how='left') 

    print("student_DoM_students_std") 
    student_DoM_students_std = data.groupby(student_DoM_select)['students'].std() 
    student_DoM_students_std.name = 'student_DoM_students_std' 
    student_DoM_students_std = student_DoM_students_std.reset_index() 
    data = pd.merge(data, student_DoM_students_std, on = student_DoM_select, how='left') 

    data['student_DoM_marks_means'].fillna(0, inplace=True) 
    data['student_DoM_students_means'].fillna(0, inplace=True) 
    data['student_DoM_marks_medians'].fillna(0, inplace=True) 
    data['student_DoM_students_medians'].fillna(0, inplace=True) 
    data['student_DoM_marks_std'].fillna(0, inplace=True) 
    data['student_DoM_students_std'].fillna(0, inplace=True) 

#Third Part: Exceptional students 

    #I think int is better here as it helps defining categories but can't use it.#  
    #print(data.isnull().sum()) 
    #print(data['types_DoM_marks_std'][data['types_DoM_marks_std']==0].sum()) 
    #data.to_csv('ex') 
    #print(data.columns) 

#Original version:#int raises the "can't convert Nan float to int. While there were no Nan as I verified in the data just before sending it to the  
    data['Except_student_IP2_DoM_marks_means']=np.array([int((data['student_IP2_DoM_marks_means'][i]-data['types_IP2_DoM_marks_means'][i])/data['types_IP2_DoM_students_std'][i]) for i in range (len(data['year']))]) 
    data['Except_student_IP2_DoM_marks_medians']=np.array([int((data['student_IP2_DoM_marks_medians'][i]-data['types_IP2_DoM_marks_means'][i])/data['types_IP2_DoM_students_std'][i]) for i in range (len(data['year']))]) 
#Second version: raises no error but final data (returned) is filled with these stupid NaN 
    data['Except_student_P2M_DoM_marks_means']=np.array([np.round((data['student_DoM_marks_means'][i]-data['types_DoM_marks_means'][i])/data['types_DoM_marks_std'][i],0) for i in range (len(data['year']))]) 
    data['Except_student_P2M_DoM_marks_medians']=np.array([np.round((data['student_DoM_marks_medians'][i]-data['types_DoM_marks_medians'][i])/data['types_DoM_marks_std'][i],0) for i in range (len(data['year']))]) 

#End 
    return data 

Answer 1

您的數據框中很可能沒有Nans，但是您正在計算中創建它們。參見以下內容：

In [15]: import pandas as pd 
In [16]: df = pd.DataFrame([[1, 2], [0, 0]], columns=['actual value', 'col2']) 
     df['means'] = df.mean(axis=1) 
     df['std'] = df.std(axis=1) 

In [17]: df 
Out[17]: 
    actual value col2 means std 
0    1  2 1.5 0.5 
1    0  0 0.0 0.0 

所以數據幀沒有任何Nans，但是計算呢？

In [21]: [(df['actual value'][i]-df['means'][i])/df['std'][i] for i in range (len(df['means']))] 
Out[21]: [-1.0, nan] 

現在，當你調用int你得到的結果列表上的錯誤。 最後，我會建議（如果可能的話）直接在底層數組中執行操作，而不是使用for循環，因爲它會快得多。

In [25]: (df['actual value']-df['means'])/df['std'] 
Out[25]: 
0 -1 
1 NaN 
dtype: float64 

這可能是不可能的，這取決於希望0分區的返回值是什麼。