我有一个数据框并尝试进行以下操作：
data['SD_rates']=np.array([int((data['actual value'][i]-data['means'][i])/data['std'][i]) for i in range (len(data['means']))])
它打破了以下消息： ＆＃34;无法将浮动Nan转换为int＆＃34;
这是我理解的错误，但是使用data.isnull（）测试了df，并且没有涉及的列包含NaN（我通过发送data.to_csv手动控制它）。
我甚至用fillna（-1，inplace = True）填充数据[＆＃39; std＆＃39;]但是，它仍然会中断。我不明白为什么，因为没有除以0（我也控制了这个列中没有零，所以没有原始0和Null / Nan填充-1），实际值和手段是fillna （0）对于缺失值，无论如何减法都不能产生一个nan（数据范围在[0-10]中）。
可能有什么不对？ （正如我所说，触发操作之前的数据是正确的......）。感谢
这是一段代码：
我的一个假设是，在某种程度上，groupby可能会产生NaN，在计算我的手段时我无法摆脱（但我相信它被大熊猫自动忽略了......）并且没有填充0或-1（我故意为标准差选择-1以避免除以0）。
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
答案 0 :(得分：2)
您的数据框中没有Nans很可能是正确的，但是您在计算中创建它们。请参阅以下内容：
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
所以数据框没有任何Nans，但是计算呢？
In [21]: [(df['actual value'][i]-df['means'][i])/df['std'][i] for i in range (len(df['means']))]
Out[21]: [-1.0, nan]
现在当你打电话给int时，你会在结果列表中收到错误。
最后，我建议（如果可能的话）直接在底层数组中执行操作，而不是使用for循环，因为它会更快。
In [25]: (df['actual value']-df['means'])/df['std']
Out[25]:
0 -1
1 NaN
dtype: float64
这可能无法实现，具体取决于需要0分区的返回值。