consolidate comment_data

instructions_analysis.py

@@ -108,6 +108,29 @@ def consolidate_csv_2():
             print(row_value)
             writer.writerow(row_value)
 
+def consolidate_csv_3():
+    rosters_dir = "/data/users/mgaughan/kkex_comment_data_121323/"
+    total_underprod_csv = pd.read_csv("kk_final_expanded_data_final.csv")
+    list_of_links = total_underprod_csv["project_name"].tolist()
+    columns = list(total_underprod_csv.columns)
+    columns.append("comments_filepath")
+    total_count=0
+    with open("kk_final_commentlist.csv", 'w', newline='') as output_file:
+        writer = csv.writer(output_file, columns)
+        writer.writerow(columns)
+        for filename in os.listdir(rosters_dir):
+            total_count += 1
+            row_value = []
+            cleaning_files = "gh_comments_"
+            pkg_name = filename[len(cleaning_files):-len(".json")]
+            print(pkg_name)
+            for item in list_of_links:
+                if pkg_name == item:
+                    row_value = total_underprod_csv.loc[total_underprod_csv["project_name"] == item].values.tolist()[0] 
+            row_value.append(rosters_dir + filename)
+            print(row_value)
+            writer.writerow(row_value)
+
 def get_main_for_splice():
     inst_doc_df = pd.read_csv("kk_final_doclist_roster.csv")
     inst_doc_df = inst_doc_df.sort_values(by=['underproduction_mean'])
@@ -150,4 +173,4 @@ def get_main_for_splice():
     print(median(all_header_counts))
 
 if __name__ == "__main__":
-    consolidate_readme()
+    consolidate_csv_3()