Fixing Pylint errors.

homemade/anomaly_detection/__init__.py

@@ -1 +1,3 @@
+"""Anomaly Detection Module"""
+
 from .gaussian_anomaly_detection import GaussianAnomalyDetection

homemade/anomaly_detection/gaussian_anomaly_detection.py

@@ -1,3 +1,5 @@
+"""Anomaly Detection Module"""
+
 import numpy as np
 import math
 
@@ -81,25 +83,25 @@ def select_threshold(labels, probabilities):
 
             # The number of false positives: the ground truth label says it’s not
             # an anomaly, but our algorithm incorrectly classified it as an anomaly.
-            fp = np.sum((predictions == 1) & (labels == 0))
+            false_positives = np.sum((predictions == 1) & (labels == 0))
 
             # The number of false negatives: the ground truth label says it’s an anomaly,
             # but our algorithm incorrectly classified it as not being anomalous.
-            fn = np.sum((predictions == 0) & (labels == 1))
+            false_negatives = np.sum((predictions == 0) & (labels == 1))
 
             # The number of true positives: the ground truth label says it’s an
             # anomaly and our algorithm correctly classified it as an anomaly.
-            tp = np.sum((predictions == 1) & (labels == 1))
+            true_positives = np.sum((predictions == 1) & (labels == 1))
 
             # Prevent division by zero.
-            if (tp + fp) == 0 or (tp + fn) == 0:
+            if (true_positives + false_positives) == 0 or (true_positives + false_negatives) == 0:
                 continue
 
             # Precision.
-            precision = tp / (tp + fp)
+            precision = true_positives / (true_positives + false_positives)
 
             # Recall.
-            recall = tp / (tp + fn)
+            recall = true_positives / (true_positives + false_negatives)
 
             # F1.
             f1 = 2 * precision * recall / (precision + recall)

homemade/k_means/__init__.py

@@ -1 +1,3 @@
+"""KMeans Module"""
+
 from .k_means import KMeans

homemade/k_means/k_means.py

@@ -1,3 +1,5 @@
+"""KMeans Module"""
+
 import numpy as np
 
 

homemade/linear_regression/__init__.py

@@ -1 +1,3 @@
+"""Linear Regression Module"""
+
 from .linear_regression import LinearRegression

homemade/logistic_regression/__init__.py

@@ -1 +1,3 @@
+"""Logistic Regression Module"""
+
 from .logistic_regression import LogisticRegression

homemade/logistic_regression/logistic_regression.py

@@ -1,3 +1,5 @@
+"""Logistic Regression Module"""
+
 import numpy as np
 from scipy.optimize import minimize
 from ..utils.features import prepare_for_training
@@ -75,6 +77,8 @@ def train(self, lambda_param=0, max_iterations=1000):
         return self.thetas, cost_histories
 
     def predict(self, data):
+        """Prediction function"""
+
         num_examples = data.shape[0]
 
         data_processed = prepare_for_training(

homemade/neural_network/__init__.py

@@ -1 +1,3 @@
+"""Neural Network Module"""
+
 from .multilayer_perceptron import MultilayerPerceptron

homemade/neural_network/multilayer_perceptron.py

@@ -1,3 +1,5 @@
+"""Neural Network Module"""
+
 import numpy as np
 from ..utils.features import prepare_for_training
 from ..utils.hypothesis import sigmoid, sigmoid_gradient
@@ -29,6 +31,8 @@ def __init__(self, data, labels, layers, epsilon, normalize_data=False):
         self.thetas = MultilayerPerceptron.thetas_init(layers, epsilon)
 
     def train(self, regularization_param=0, max_iterations=1000, alpha=1):
+        """Train the model"""
+
         # Flatten model thetas for gradient descent.
         unrolled_thetas = MultilayerPerceptron.thetas_unroll(self.thetas)
 
@@ -65,7 +69,7 @@ def predict(self, data):
 
     @staticmethod
     def gradient_descent(
-        data, labels, unrolled_theta, layers, regularization_param, max_iteration, alpha
+            data, labels, unrolled_theta, layers, regularization_param, max_iteration, alpha
     ):
         """Gradient descent function.
 
@@ -187,6 +191,8 @@ def cost_function(data, labels, thetas, layers, regularization_param):
 
     @staticmethod
     def feedforward_propagation(data, thetas, layers):
+        """Feedforward propagation function"""
+
         # Calculate the total number of layers.
         num_layers = len(layers)
 

homemade/utils/features/__init__.py

@@ -1,3 +1,5 @@
+"""Dataset Features Related Utils"""
+
 from .normalize import normalize
 from .add_polynomials import add_polynomials
 from .add_sinusoids import add_sinusoids

homemade/utils/hypothesis/__init__.py

@@ -1,2 +1,4 @@
+"""Dataset Hypothesis Related Utils"""
+
 from .sigmoid import sigmoid
 from .sigmoid_gradient import sigmoid_gradient

notebooks/anomaly_detection/anomaly_detection_gaussian_demo.ipynb

@@ -377,7 +377,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -426,7 +426,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -482,7 +482,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -491,7 +491,7 @@
        "[]"
       ]
      },
-     "execution_count": 25,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     },