Python can't take input while using functions

Question

While building my model, I figured that it makes sense to reuse some of the code that I've been using for the train dataset, on the test set as well so I took the code performing mutual operations into one function definition. In this function, I am handling missing values and using its return to perform one-hot-encoding and using it on Random Forest Regression. However, its throwing the following error:

Traceback (most recent call last):
  File "C:/Users/security/Downloads/AP/Boston-Kaggle/Model.py", line 56, in <module>
    sel.fit(x_train, y_train)
  File "C:\Users\security\AppData\Roaming\Python\Python37\site-packages\sklearn\feature_selection\from_model.py", line 196, in fit
    self.estimator_.fit(X, y, **fit_params)
  File "C:\Users\security\AppData\Roaming\Python\Python37\site-packages\sklearn\ensemble\forest.py", line 249, in fit
    X = check_array(X, accept_sparse="csc", dtype=DTYPE)
  File "C:\Users\security\AppData\Roaming\Python\Python37\site-packages\sklearn\utils\validation.py", line 542, in check_array
    allow_nan=force_all_finite == 'allow-nan')
  File "C:\Users\security\AppData\Roaming\Python\Python37\site-packages\sklearn\utils\validation.py", line 56, in _assert_all_finite
    raise ValueError(msg_err.format(type_err, X.dtype))
ValueError: Input contains NaN, infinity or a value too large for dtype('float32').

I did not have this problem while using the same code without organizing it into a function. def feature_selection_and_engineering(df) is the function in question. The following is my entire code.

import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_selection import SelectFromModel
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor

train = pd.read_csv("https://raw.githubusercontent.com/oo92/Boston-Kaggle/master/train.csv")
test = pd.read_csv("https://raw.githubusercontent.com/oo92/Boston-Kaggle/master/test.csv")

def feature_selection_and_engineering(df):
    # Creating a series of how many NaN's are in each column
    nan_counts = df.isna().sum()

    # Creating a template list
    nan_columns = []

    # Iterating over the series and if the value is more than 0 (i.e there are some NaN's present)
    for i in range(0, len(nan_counts)):
        if nan_counts[i] > 0:
            nan_columns.append(df.columns[i])

    # Iterating through all the columns which are known to have NaN's
    for i in nan_columns:
        if df[nan_columns][i].dtypes == 'float64':
            df[i] = df[i].fillna(df[i].mean())
        elif df[nan_columns][i].dtypes == 'object':
            df[i] = df[i].fillna('XX')

    # Creating a template list
    categorical_columns = []

    # Iterating across all the columns,
    # checking if they're of the object datatype and if they are, appending them to the categorical list
    for i in range(0, len(df.dtypes)):
        if df.dtypes[i] == 'object':
            categorical_columns.append(df.columns[i])

    return categorical_columns

# take one-hot encoding
OHE_sdf = pd.get_dummies(feature_selection_and_engineering(train))

# drop the old categorical column from original df
train.drop(columns = feature_selection_and_engineering(train), axis = 1, inplace = True)

# attach one-hot encoded columns to original data frame
train = pd.concat([train, OHE_sdf], axis = 1, ignore_index = False)

# Dividing the training dataset into train/test sets with the test size being 20% of the overall dataset.
x_train, x_test, y_train, y_test = train_test_split(train, train['SalePrice'], test_size = 0.2, random_state = 42)

randomForestRegressor = RandomForestRegressor(n_estimators=1000)

# Invoking the Random Forest Classifier with a 1.25x the mean threshold to select correlating features
sel = SelectFromModel(RandomForestClassifier(n_estimators = 100), threshold = '1.25*mean')
sel.fit(x_train, y_train)

selected = sel.get_support()

# linearRegression.fit(x_train, y_train)
randomForestRegressor.fit(x_train, y_train)

# Assigning the accuracy of the model to the variable "accuracy"
accuracy = randomForestRegressor.score(x_train, y_train)

# Predicting for the data in the test set
predictions = randomForestRegressor.predict(feature_selection_and_engineering(test))

# Writing the predictions to a new CSV file
submission = pd.DataFrame({'Id': test['PassengerId'], 'SalePrice': predictions})
filename = 'Boston-Submission.csv'
submission.to_csv(filename, index=False)

print(accuracy*100, "%")