data_analysis.py 文件源码

def create_model(self, training_articles):
        model = OneVsRestClassifier(svm.SVC(probability=True))

        features = []
        labels = []
        i = 0
        for article in training_articles:
            print("Generating features for article " + str(i) + "...")
            google_cloud_response = self.analyze_text_google_cloud(article["article"])
            relevant_entities = self.get_relevant_entities(google_cloud_response["entities"], article["market"]["entities"], article["market"]["wikipedia_urls"])

            # Only count this article if a relevant entity is present
            if relevant_entities:
                article_features = self.article_features(relevant_entities, article["market"], google_cloud_response, article["article"])
                features.append(article_features)
                labels.append(article["label"])
            else:
                print("Skipping article " + str(i) + "...")

            i = i + 1

        print("Performing feature scaling...")
        scaler = preprocessing.StandardScaler().fit(features)
        features_scaled = scaler.transform(features)

        print("Fitting model...")
        model.fit(features_scaled, labels)

        print("Saving model...")
        joblib.dump(scaler, "data_analysis/caler.pkl")
        joblib.dump(model, "data_analysis/model.pkl")

        print("Done!")

    # For use in prod