add names count, blacken

parse.py

@@ -6,16 +6,52 @@ import numpy as np
 from collections import Counter
 from pprint import pprint
 
-stop_words = ['of', 'and', 'the', 'we', 'in', 'to', 'what', 'a', 'on', 'an',
-              'do', 'for', 'with', 'is', 'it', 'that', 'this', 'as', 'by',
-              'are', 'using', 'from', 'how', 'has', 'be', 'or', 'can', 'our',
-              'at', 'why', 'when', 'introduction', 'your', 'through']
-file_path = 'data.csv'
+stop_words = [
+    "of",
+    "and",
+    "the",
+    "we",
+    "in",
+    "to",
+    "what",
+    "a",
+    "on",
+    "an",
+    "do",
+    "for",
+    "with",
+    "is",
+    "it",
+    "that",
+    "this",
+    "as",
+    "by",
+    "are",
+    "using",
+    "from",
+    "how",
+    "has",
+    "be",
+    "or",
+    "can",
+    "our",
+    "at",
+    "why",
+    "when",
+    "introduction",
+    "your",
+    "through",
+    "et",
+    "al.",
+    "&",
+    "",
+]
+file_path = "data.csv"
 data = []
 
 
 def parse_csv(file_path):
-    with open(file_path, 'r') as file:
+    with open(file_path, "r") as file:
         reader = csv.reader(file)
         for row in reader:
             data.append(row)
@@ -35,10 +71,10 @@ def extract_title_keywords(data):
     title_keywords = []
     re_words = []
     for row in data:
-        raw_words = row[2].split(' ')
+        raw_words = row[2].split(" ")
         row_words = []
         for word in raw_words:
-            re_word = re.sub(r'[^a-zA-Z\-]', '', word.lower()) 
+            re_word = re.sub(r"[^a-zA-Z\-]", "", word.lower())
             if re_word not in stop_words:
                 re_words.append(re_word)
                 row_words.append(re_word)
@@ -50,22 +86,33 @@ def print_title_keywords(data):
     title_keywords = extract_title_keywords(data)
     title_keywords = [word[0] for word in title_keywords]
     count_title_words = Counter(title_keywords).most_common(20)
-    pprint(count_title_words) 
+    pprint(count_title_words)
 
 
 def histogram(data):
-    dates = [] 
+    dates = []
     for row in data:
         dates.append(int(row[4]))
-    years = range(min(dates), max(dates)+2)
+    years = range(min(dates), max(dates) + 2)
     plt.hist(dates, bins=years)
     plt.show()
 
 
-if __name__ == '__main__':
+def names(data):
+    names = []
+    for row in data:
+        name_parts = row[1].split(" ")
+        for name in name_parts:
+            if name not in stop_words:
+                names.append(name)
+    count_names = Counter(names).most_common(20)
+    pprint(count_names)
+
+
+if __name__ == "__main__":
     parse_csv(file_path)
     data = data[1:]
     extract_journal_titles(data)
     print_title_keywords(data)
-    dash_viz(data)
+    names(data)
     histogram(data)