[+] Create function to remove outliers

requirements.txt

@@ -1,25 +1,28 @@
 
+####################
+# Data Collection
 # Json5 is a human-readable json format that allows for things such as unquoted keys or comments.
 json5~=0.9.6
-
 # Tweepy is a python SDK for twitter
 tweepy==4.4.0
-
 # requests is for getting html from a website URL
 requests==2.26.0
-
 # beautifulsoup is used to extract data from html
 beautifulsoup4==4.10.0
 
-# 7zip packing utility for packing our processed data
-py7zr==0.16.3
-
 #####################
-# Data visualization
+# Data Visualization
 # Print table data
 tabulate==0.8.9
 # Draw local graphs
 matplotlib==3.5.0
+# Calculate data statistics
+numpy==1.21.4
+
+####################
+# Data Packing
+# 7zip packing utility for packing our processed data
+py7zr==0.16.3
 
 #####################
 # Testing and code checking

src/utils.py

@@ -8,6 +8,7 @@ from pathlib import Path
 from typing import Union
 
 import json5
+import numpy as np
 
 
 @dataclass
@@ -98,6 +99,29 @@ def read(file: str) -> str:
         return f.read()
 
 
+def remove_outliers(points: list[float], z_threshold: float = 3.5) -> list[float]:
+    """
+    Create list with outliers removed for graphing
+
+    Credit to: https://stackoverflow.com/a/11886564/7346633
+
+    :param points: Input points list
+    :param z_threshold: Z threshold for identifying whether or not a point is an outlier
+    :return: List with outliers removed
+    """
+    points = np.array(points)
+    if len(points.shape) == 1:
+        points = points[:, None]
+    median = np.median(points, axis=0)
+    diff = np.sum((points - median)**2, axis=-1)
+    diff = np.sqrt(diff)
+    med_abs_deviation = np.median(diff)
+
+    modified_z_score = 0.6745 * diff / med_abs_deviation
+
+    is_outlier = modified_z_score > z_threshold
+
+
 class EnhancedJSONEncoder(json.JSONEncoder):
     def default(self, o):