Tighten up psf/black and flake8 (#2024)

* Tighten up psf/black and flake8

* Fix some tests

* Fix some E741

* Fix some E741

* updating DIRECTORY.md

Co-authored-by: github-actions <${GITHUB_ACTOR}@users.noreply.github.com>

machine_learning/k_means_clust.py

@@ -11,9 +11,11 @@ Python:
 Inputs:
   - X , a 2D numpy array of features.
   - k , number of clusters to create.
-  - initial_centroids , initial centroid values generated by utility function(mentioned in usage).
+  - initial_centroids , initial centroid values generated by utility function(mentioned
+    in usage).
   - maxiter , maximum number of iterations to process.
-  - heterogeneity , empty list that will be filled with hetrogeneity values if passed to kmeans func.
+  - heterogeneity , empty list that will be filled with hetrogeneity values if passed
+    to kmeans func.
 
 Usage:
   1. define 'k' value, 'X' features array and 'hetrogeneity' empty list
@@ -22,7 +24,8 @@ Usage:
         initial_centroids = get_initial_centroids(
             X,
             k,
-            seed=0 # seed value for initial centroid generation, None for randomness(default=None)
+            seed=0 # seed value for initial centroid generation,
+                   # None for randomness(default=None)
             )
 
   3. find centroids and clusters using kmeans function.
@@ -37,7 +40,8 @@ Usage:
             )
 
 
-  4. Plot the loss function, hetrogeneity values for every iteration saved in hetrogeneity list.
+  4. Plot the loss function, hetrogeneity values for every iteration saved in
+     hetrogeneity list.
         plot_heterogeneity(
             heterogeneity,
             k
@@ -46,8 +50,9 @@ Usage:
   5. Have fun..
 
 """
-from sklearn.metrics import pairwise_distances
 import numpy as np
+from matplotlib import pyplot as plt
+from sklearn.metrics import pairwise_distances
 
 TAG = "K-MEANS-CLUST/ "
 
@@ -118,9 +123,6 @@ def compute_heterogeneity(data, k, centroids, cluster_assignment):
     return heterogeneity
 
 
-from matplotlib import pyplot as plt
-
-
 def plot_heterogeneity(heterogeneity, k):
     plt.figure(figsize=(7, 4))
     plt.plot(heterogeneity, linewidth=4)
@@ -136,9 +138,11 @@ def kmeans(
 ):
     """This function runs k-means on given data and initial set of centroids.
        maxiter: maximum number of iterations to run.(default=500)
-       record_heterogeneity: (optional) a list, to store the history of heterogeneity as function of iterations
+       record_heterogeneity: (optional) a list, to store the history of heterogeneity
+                             as function of iterations
                              if None, do not store the history.
-       verbose: if True, print how many data points changed their cluster labels in each iteration"""
+       verbose: if True, print how many data points changed their cluster labels in
+                             each iteration"""
     centroids = initial_centroids[:]
     prev_cluster_assignment = None
 
@@ -149,7 +153,8 @@ def kmeans(
         # 1. Make cluster assignments using nearest centroids
         cluster_assignment = assign_clusters(data, centroids)
 
-        # 2. Compute a new centroid for each of the k clusters, averaging all data points assigned to that cluster.
+        # 2. Compute a new centroid for each of the k clusters, averaging all data
+        #    points assigned to that cluster.
         centroids = revise_centroids(data, k, cluster_assignment)
 
         # Check for convergence: if none of the assignments changed, stop

machine_learning/linear_discriminant_analysis.py

@@ -186,7 +186,8 @@ def predict_y_values(
     >>> means = [5.011267842911003, 10.011267842911003, 15.011267842911002]
     >>> variance = 0.9618530973487494
     >>> probabilities = [0.3333333333333333, 0.3333333333333333, 0.3333333333333333]
-    >>> predict_y_values(x_items, means, variance, probabilities) # doctest: +NORMALIZE_WHITESPACE
+    >>> predict_y_values(x_items, means, variance,
+    ...                  probabilities)  # doctest: +NORMALIZE_WHITESPACE
     [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1,
     1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
     2, 2, 2, 2, 2, 2, 2, 2, 2]
@@ -211,7 +212,7 @@ def predict_y_values(
             # appending discriminant values of each item to 'results' list
             results.append(temp)
 
-    return [l.index(max(l)) for l in results]
+    return [result.index(max(result)) for result in results]
 
 
 # Calculating Accuracy

machine_learning/polymonial_regression.py

@@ -1,5 +1,12 @@
 import matplotlib.pyplot as plt
 import pandas as pd
+from sklearn.linear_model import LinearRegression
+
+# Splitting the dataset into the Training set and Test set
+from sklearn.model_selection import train_test_split
+
+# Fitting Polynomial Regression to the dataset
+from sklearn.preprocessing import PolynomialFeatures
 
 # Importing the dataset
 dataset = pd.read_csv(
@@ -9,16 +16,9 @@ X = dataset.iloc[:, 1:2].values
 y = dataset.iloc[:, 2].values
 
 
-# Splitting the dataset into the Training set and Test set
-from sklearn.model_selection import train_test_split
-
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
 
 
-# Fitting Polynomial Regression to the dataset
-from sklearn.preprocessing import PolynomialFeatures
-from sklearn.linear_model import LinearRegression
-
 poly_reg = PolynomialFeatures(degree=4)
 X_poly = poly_reg.fit_transform(X)
 pol_reg = LinearRegression()

machine_learning/scoring_functions.py

@@ -14,6 +14,7 @@ import numpy as np
     and types of data
 """
 
+
 # Mean Absolute Error
 def mae(predict, actual):
     """