Kiwibp

wordcloud = WordCloud(background_color='white', mode = "RGB", width = 2000, height=1000).generate(str(postings['name']))
plt.title("Craigslist Used Items Word Cloud")
plt.imshow(wordcloud)
plt.axis("off")
plt.show();

Kiwibp

# Tree-based estimators can be used to compute feature importances, which in turn can be used to discard irrelevant features.
clf = RandomForestClassifier(n_estimators=50, max_features='sqrt')
clf = clf.fit(train, targets)

# Let's have a look at the importance of each feature.
features = pd.DataFrame()
features['feature'] = train.columns
features['importance'] = clf.feature_importances_

# Sorting values by feature importance.

Kiwibp

logreg = LogisticRegression()
logreg_cv = LogisticRegressionCV()
rf = RandomForestClassifier()
gboost = GradientBoostingClassifier()
svm = SVC(probability=True)
knn = KNeighborsClassifier()
dt = DecisionTreeClassifier()

models = [logreg, logreg_cv, rf, gboost, svm, knn, dt]

Kiwibp

# train the model on the training set
gboost.fit(X_train, y_train)

# make class predictions for the testing set
y_pred_class = gboost.predict(X_test)

# IMPORTANT: first argument is true values, second argument is predicted values
print(metrics.confusion_matrix(y_test, y_pred_class))

binary = np.array([[125, 14],