if y_true[i] == pos:
TP += 1
else:
FP += 1
FPR = FP / num_neg
TPR = TP / num_pos
if verbose: print("{},{}".format(FPR, TPR))
if __name__ == "__main__":
if len(sys.argv) == 1:
k = 30
train = "datasets/votes_train.json"
test = "datasets/votes_test.json"
else:
k = int(sys.argv[1])
train = str(sys.argv[2])
test = str(sys.argv[3])
# parse the json files for data
X_train, y_train, meta_train = parse_json(train)
X_test, y_test, meta_test = parse_json(test)
# fit KNN and predict confidence
knn = KNNClassifier(k=k)
knn.fit(X_train, y_train, meta_train)
y_conf = knn.predict(X_test, verbose=False, confidence=True)
roc_curve(y_test, y_conf, meta_test, verbose=True)
max_k = int(sys.argv[1])
train = str(sys.argv[2])
val = str(sys.argv[3])
test = str(sys.argv[4])
# parse the json files for data
X_train, y_train, meta_train = parse_json(train)
X_val, y_val, meta_val = parse_json(val)
X_test, y_test, meta_test = parse_json(test)
# train classifier on TRAIN, predict on VAL (for k=1,2,...,max_k)
acc = {}
for k in range(1, max_k + 1):
knn = KNNClassifier(k=k)
knn.fit(X_train, y_train, meta_train)
y_pred = knn.predict(X_val, verbose=False)
acc[k] = accuracy_score(y_val, y_pred)
print("{},{}".format(k, acc[k]))
best_k = max(acc, key=lambda key: acc[
key]) # note that 'max' always returns first value in case of ties
print(best_k)
# train on TRAIN + VAL, predict on TEST
knn_best = KNNClassifier(k=best_k)
X_train_val = pd.concat([X_train, X_val], ignore_index=True)
y_train_val = pd.concat([y_train, y_val], ignore_index=True)
knn_best.fit(X_train_val, y_train_val, meta_train)
# Create the k-NN object.
knn = KNNClassifier(train_X[:, 1:], train_y[:, 1:], metric='euclidean')
# Iterate through all possible values of k:
for k in range(min_k, max_k + 1):
knn.set_k(k)
# 1. Perform KNN training and classify all the test points. In this step, you will
# obtain a prediction for each test point.
y_pred = []
for i in range(test_X.shape[0]):
result = knn.predict(test_X[i, 1:])
if result:
y_pred.append(result)
else:
knn.set_k(k - 1)
y_pred.append(knn.predict(test_X[i, 1:]))
knn.set_k(k)
y_pred = np.array(y_pred)
# 2. Compute performance metrics given the true-labels vector and the predicted-
# labels vector (you might consider to use obtain_performance_metrics() function)
perf = obtain_performance_metrics(test_y[:, 1], y_pred)
# 3. Write performance results in the output file, as indicated the in homework
import pandas as pd
if __name__ == "__main__":
if len(sys.argv) == 1:
k = 10
train = "datasets/votes_train.json"
test = "datasets/votes_test.json"
else:
k = int(sys.argv[1])
train = str(sys.argv[2])
test = str(sys.argv[3])
# parse the json files for data
X_train, y_train, meta_train = parse_json(train)
X_test, y_test, meta_test = parse_json(test)
for i in range(10):
N = X_train.shape[0]
ind = math.floor(
(i + 1) * N / 10 - 1) # subtract 1 since indexing starts at 0
knn = KNNClassifier(k=k)
knn.fit(X_train.ix[0:ind, :], y_train.ix[0:ind], meta_train)
y_pred = knn.predict(X_test, verbose=False)
acc = accuracy_score(y_test, y_pred)
print(X_train.ix[0:ind, :].shape[0], end="")
print(",{}".format(acc))
