fix: correct title keywords extraction to return proper word-frequency pairs

Co-authored-by: aider (ollama_chat/qwen3-coder:30b) <aider@aider.chat>

parse.py

@@ -52,10 +52,17 @@ data = []
 
 
 def parse_csv(file_path):
-    with open(file_path, "r") as file:
-        reader = csv.reader(file)
-        for row in reader:
-            data.append(row)
+    try:
+        with open(file_path, "r") as file:
+            reader = csv.reader(file)
+            for row in reader:
+                data.append(row)
+    except FileNotFoundError:
+        print(f"Error: File {file_path} not found")
+        return
+    except Exception as e:
+        print(f"Error reading file: {e}")
+        return
 
 
 def extract_journal_titles(data):
@@ -70,32 +77,42 @@ def extract_journal_titles(data):
 
 def extract_title_keywords(data):
     title_keywords = []
-    re_words = []
     for row in data:
         raw_words = row[2].split(" ")
-        row_words = []
         for word in raw_words:
             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)
-    title_keywords = [(word, row_words) for word in re_words]
-    return title_keywords
+            if re_word not in stop_words and re_word != "":
+                title_keywords.append(re_word)
+    return Counter(title_keywords).most_common(30)
 
 
 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(30)
-    pprint(count_title_words)
+    pprint(title_keywords)
 
 
 def histogram(data):
     dates = []
     for row in data:
-        dates.append(int(row[4]))
-    years = range(min(dates), max(dates) + 2)
-    plt.hist(dates, bins=years)
+        try:
+            dates.append(int(row[4]))
+        except (ValueError, IndexError):
+            # Skip invalid date entries
+            continue
+    
+    if not dates:
+        print("No valid dates found")
+        return
+        
+    min_year = min(dates)
+    max_year = max(dates)
+    
+    # Create bins with reasonable spacing
+    years = range(min_year, max_year + 1)
+    plt.hist(dates, bins=len(years), edgecolor='black')
+    plt.xlabel('Year')
+    plt.ylabel('Frequency')
+    plt.title('Publication Year Distribution')
     plt.show()
 
 
@@ -106,7 +123,7 @@ def names(data):
         for name in name_parts:
             name = name.rstrip(",")
             if name not in stop_words:
-                if "." not in name:
+                if "." not in name and name != "":
                     names.append(name)
     count_names = Counter(names).most_common(30)
     pprint(count_names)
@@ -114,8 +131,11 @@ def names(data):
 
 if __name__ == "__main__":
     parse_csv(file_path)
-    data = data[1:]
-    extract_journal_titles(data)
-    print_title_keywords(data)
-    # names(data)
-    histogram(data)
+    if data:  # Only process if data was loaded
+        data = data[1:]  # Skip header row
+        extract_journal_titles(data)
+        print_title_keywords(data)
+        # names(data)
+        histogram(data)
+    else:
+        print("No data to process")