python - AttributeError: 'super' object has no attribute 'sklearn_tags' when using GridSearchCV

admin管理员组

文章数量:1305243

I am working on a binary classification problem using a neural network with TensorFlow/Keras and scikit-learn's GridSearchCV for hyperparameter tuning. However, I am encountering an AttributeError when trying to fit the GridSearchCV object. The error occurs at the line grid_result = grid.fit(X_train, y_train). Here is my complete code:

import pandas as pd
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import StandardScaler, LabelEncoder, OneHotEncoder
from sklearn.pipeline import Pipeline
from scikeras.wrappers import KerasClassifier
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.callbacks import EarlyStopping
import pickle

# Load and preprocess data
data = pd.read_csv('Churn_Modelling.csv')
data = data.drop(['RowNumber', 'CustomerId', 'Surname'], axis=1)

label_encoder_gender = LabelEncoder()
data['Gender'] = label_encoder_gender.fit_transform(data['Gender'])

onehot_encoder_geo = OneHotEncoder(handle_unknown='ignore')
geo_encoded = onehot_encoder_geo.fit_transform(data[['Geography']]).toarray()
geo_encoded_df = pd.DataFrame(geo_encoded, columns=onehot_encoder_geo.get_feature_names_out(['Geography']))

data = pd.concat([data.drop('Geography', axis=1), geo_encoded_df], axis=1)

X = data.drop('Exited', axis=1)
y = data['Exited']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Save encoders and scaler for later use
with open('label_encoder_gender.pkl', 'wb') as file:
    pickle.dump(label_encoder_gender, file)

with open('onehot_encoder_geo.pkl', 'wb') as file:
    pickle.dump(onehot_encoder_geo, file)

with open('scaler.pkl', 'wb') as file:
    pickle.dump(scaler, file)

# Define the model creation function
def create_model(neurons=32, layers=1):
    model = Sequential()
    model.add(Dense(neurons, activation='relu', input_shape=(X_train.shape[1],)))

    for _ in range(layers - 1):
        model.add(Dense(neurons, activation='relu'))

    model.add(Dense(1, activation='sigmoid'))
    modelpile(optimizer='adam', loss="binary_crossentropy", metrics=['accuracy'])

    return model

# Create a Keras classifier
model = KerasClassifier(layers=1, neurons=32, build_fn=create_model, verbose=1)

# GridSearch parameters
param_grid = {
    'neurons': [16, 32, 64, 128],
    'layers': [1, 2],
    'epochs': [50, 100]
}

# Perform grid search
grid = GridSearchCV(estimator=model, param_grid=param_grid, n_jobs=-1, cv=3, verbose=1)
grid_result = grid.fit(X_train, y_train)  # Error occurs here

# Print the best parameters
print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))

I ensured that all libraries (scikeras, tensorflow, scikit-learn) are up to date.

本文标签：