Google Machine Learning Engine deployment_uri Erro

Question

I'm new to Machine learning world and I have build a model using SKlearn by implementing the Isolation Forest and Local Outlier Factor classifiers.Now I'm working on the deployment of this model. I have exported the trained model to a Pickle file as:

from sklearn.metrics import classification_report, accuracy_score
from sklearn.ensemble import IsolationForest
from sklearn.neighbors import LocalOutlierFactor

# define a random state
state = 1

# define the outlier detection method
classifiers = {
    "Isolation Forest": IsolationForest(max_samples=len(X),
                                       contamination=outlier_fraction,
                                       random_state=state),
    "Local Outlier Factor": LocalOutlierFactor(
    n_neighbors = 20,
    contamination = outlier_fraction)
}
from sklearn.externals import joblib
# fit the model
n_outliers = len(Fraud)

for i, (clf_name, clf) in enumerate(classifiers.items()):

    # fit te data and tag outliers
    if clf_name == "Local Outlier Factor":
        y_pred = clf.fit_predict(X)
        # Export the classifier to a file
        joblib.dump(clf, 'model.joblib')
        scores_pred = clf.negative_outlier_factor_
    else:
        clf.fit(X)
        scores_pred = clf.decision_function(X)
        y_pred = clf.predict(X)
        # Export the classifier to a file
        joblib.dump(clf, 'model.joblib')

    # Reshape the prediction values to 0 for valid and 1 for fraudulent
    y_pred[y_pred == 1] = 0
    y_pred[y_pred == -1] = 1

    n_errors = (y_pred != Y).sum()

    # run classification metrics 
    print('{}:{}'.format(clf_name, n_errors))
    print(accuracy_score(Y, y_pred ))
    print(classification_report(Y, y_pred ))

Then I have created a storage bucket on Google Cloud and upload this model.joblib to file to that bucket. After that when I have try to create a ML Engine version it throws an error as:

Field: version.deployment_uri Error: Deployment directory gs://fdmlmodel_01/ is expected to contain exactly one of: [saved_model.pb, saved_model.pbtxt].

As i'm new to machine learning, how can i solve this issue or is there a proper step by step tutorial to deploy this model to Google Cloud ML Engine.

Help me, please!

Thanks in advance!

Answer 1

Please refer this docs and official docs to build and deploy scikit-learn model in cloud-ml.

To Save as pickle file,

import pickle
with open('model.pkl', 'wb') as model_file:
pickle.dump(classifier, model_file)