snapshot...

modules/machine_learning/classification.py

@@ -7,6 +7,7 @@ import matplotlib.pyplot as plt
 from sklearn.metrics import confusion_matrix, classification_report, accuracy_score, jaccard_score, f1_score, precision_score, recall_score, roc_auc_score
 from sklearn.model_selection import train_test_split
 from sklearn.linear_model import LogisticRegression
+from sklearn.neighbors import KNeighborsClassifier
 
 
 def get_csv_as_dataframe(csv_file):
@@ -58,6 +59,29 @@ def logistic_regression(x, y):
     yhat = LR.predict(x_test)
     yhat_prob = LR.predict_proba(x_test)
 
+    print(confusion_matrix(y_test, yhat, labels=[1,0]))
+    print('Accuracy:    ', accuracy_score(y_test, yhat))
+    print('Jaccard Idx: ', jaccard_score(y_test, yhat))
+    print('Precision:   ', precision_score(y_test, yhat))
+    print('Recall:      ', recall_score(y_test, yhat))
+    print('F1:          ', f1_score(y_test, yhat))
+    print('AUC:         ', roc_auc_score(y_test, yhat_prob[:, 1]))
+
+
+def k_nearest_neighbors(x, y, k=4):
+    x_train, x_test, y_train, y_test = train_test_split( x, y, test_size=0.2, random_state=4)
+    print('Train set:', x_train.shape,  y_train.shape)
+    print('Test set:', x_test.shape,  y_test.shape)
+
+    x_train = np.where(np.isnan(x_train), 0, x_train)
+    x_test = np.where(np.isnan(x_test), 0, x_test)
+    print('num no icing test: ', np.sum(y_test == 0))
+    print('num icing test: ', np.sum(y_test == 1))
+
+    KN_C = KNeighborsClassifier(n_neighbors=k).fit(x_train, y_train)
+    yhat = KN_C.predict(x_test)
+    yhat_prob = KN_C.predict_proba(x_test)
+
     print(confusion_matrix(y_test, yhat, labels=[1,0]))
     print('Accuracy:    ', accuracy_score(y_test, yhat))
     print('Jaccard Idx: ', jaccard_score(y_test, yhat))