mend

src/create_cooccurrence_matrix.py

@@ -1,5 +1,6 @@
 import pandas as pd
 import re
+import numpy as np
 
 tweets_path = "../raw_data/tweets.csv"
 accounts_path = "../raw_data/accounts.txt"
@@ -32,5 +33,19 @@ mention_counts = tweets[["handle", "mentions"]].value_counts().reset_index()
 cooc_matrix = pd.DataFrame(mention_counts).pivot(index="handle", columns="mentions",
         values=0).reset_index()
 
+cooc_matrix.set_index("handle",inplace=True)
+
+# networkx wants the matrix to be square, so make sure it is suare
+# add columns
+for r in cooc_matrix.index:
+    if r not in cooc_matrix.columns:
+        print(f"{r} is not in colums")
+        cooc_matrix[r] = None
+
+not_in_index = list(filter(lambda x: x not in cooc_matrix.index, cooc_matrix.columns))
+new_rows = pd.DataFrame(index=not_in_index)
+cooc_matrix = pd.concat([cooc_matrix, new_rows])
+
+
 #save cooccurence matrix
-cooc_matrix.to_csv(output_path, sep=";", index=False)
+cooc_matrix.to_csv(output_path, sep=";")