找到具有 0 个特征 (shape=(10792, 0)) 的数组，而至少需要 1 个

Question

Hey I am using Jupitor Notebook and doing machine learning. I wrote this code but getting this error and I dont know what is the error. This is my code for reference:

f`rom sklearn.experimental import enable_iterative_imputer
from sklearn.impute import IterativeImputer

imp = IterativeImputer(random_state=42)

date = pd.Timestamp('2200-01-01')

for col in combi:
    if combi[col].dtype=="object":
        combi[col].fillna("not listed", inplace=True)
    if combi[col].dtype=="int":
        #X[col].fillna(X[col].mode()[0], inplace=True)
        combi[col].fillna(combi[col].mean(), inplace=True)
        #combi[col] = combi[col].astype.int()
    if combi[col].dtype=='float':
       #X[col].fillna(X[col].mean(), inplace=True)
       combi[col] = imp.fit_transform(combi[col].values.reshape(-1,1))
    if combi[col].dtype=="datetime64[ns]":
        combi[col].fillna(date, inplace=True)
combi`

Solution of the problem

Answer 1

This is not how for loops work in Python.

for col in combi:
    if combi[col].dtype=="object":
        # ...

col isn't an index into the collection you're iterating over ( combi ), it is the dereferenced element itself. Change all instances of combi[col] inside your for loop to col to correct. Example:

for col in combi:
    if col.dtype=="object":

You didn't post all of your code so it's unclear if this will resolved the problem you're seeing, but it is certainly a step in the right direction.