x_test /= 255.
# getting model predictions
test_predictions = model.predict(x_test)
labels_ohe_names = pd.get_dummies(target_labels, sparse=True)
predictions = pd.DataFrame(test_predictions,
columns=labels_ohe_names.columns)
predictions = list(predictions.idxmax(axis=1))
test_labels = list(y_test)
#evaluate model performance
meu.get_metrics(true_labels=test_labels, predicted_labels=predictions)
meu.display_classification_report(true_labels=test_labels,
predicted_labels=predictions,
classes=list(labels_ohe_names.columns))
# print(meu.display_confusion_matrix_pretty(true_labels=test_labels,
# predicted_labels=predictions,
# classes=list(labels_ohe_names.columns)))
font = {'family': 'Times New Roman', 'size': 12}
matplotlib.rc('font', **font)
mat = confusion_matrix(test_labels, predictions)
plot_confusion_matrix(conf_mat=mat,
figsize=(4, 4),
class_names=list(labels_ohe_names.columns),
show_normed=False)
grid_width = 5
# test for a given comment's best features
eli5.show_prediction(svm_best[1], test_corpus[8], vec=svm_best[0], top=10)
# ### model performance evaluation with Linear SVM
# +
import model_evaluation_utils as meu
svm_predictions = gs_svm.predict(test_corpus)
unique_classes = list(set(test_label_nums))
meu.get_metrics(true_labels=test_label_nums, predicted_labels=svm_predictions)
# -
meu.display_classification_report(true_labels=test_label_nums,
predicted_labels=svm_predictions,
classes=unique_classes)
from confusion_matrices import confusion_matrices
confusion_matrices(test_label_nums, svm_predictions)
# ### checking mismatched values
# Extract test document row numbers
train_idx, test_idx = train_test_split(np.array(range(len(data_df['review']))), test_size=0.33, random_state=42)
test_idx
svm_predictions = gs_svm.predict(test_corpus)
test_df = data_df.iloc[test_idx]
test_df['predicted label'] = svm_predictions