From 2033e638f2042de8cbd8ac915de196a01e00e304 Mon Sep 17 00:00:00 2001
From: Daniel <59575049+lemoentjiez@users.noreply.github.com>
Date: Tue, 27 Dec 2022 01:29:34 +0200
Subject: [PATCH] Update network.py

---
 LabMD_3/network.py | 52 +++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 45 insertions(+), 7 deletions(-)

diff --git a/LabMD_3/network.py b/LabMD_3/network.py
index 8f70c15..8216267 100644
--- a/LabMD_3/network.py
+++ b/LabMD_3/network.py
@@ -4,17 +4,19 @@ import nltk
 from nltk import TweetTokenizer
 
 tt = TweetTokenizer()
-special_chars = "1234567890.=?\",”$%^&’*(…):!><"
-
+special_chars = "1234567890.=?\",”$%^;&’*(…):!><"
+special_chars_CSV = "1234567890.=?\",”;$%^&’*(…):@!>#@<"
 words_tweet_tokenizer = []
 words_per_tweet = {}
 special_words = []
 hashtags = []
+wordsForCSV = []
 
 # Handles the tweet json, separates words into needed categories, and extracts hashtags
 with open("tweets.json", "r", encoding="utf-8") as tweetJson:
     tweetJsonData = json.load(tweetJson)
     for tweet in tweetJsonData:
+        tempAppend = []
         tempWords = tt.tokenize(tweet["text"])
         words_per_tweet[tweet["id"]] = tempWords
         for word in tempWords:
@@ -25,12 +27,14 @@ with open("tweets.json", "r", encoding="utf-8") as tweetJson:
             else:
                 if len(word) > 1:
                     special_words.append(word)
+            if not any(c in special_chars_CSV for c in word) and len(word) > 1:
+                tempAppend.append(word)
+        wordsForCSV.append(tempAppend)
 
 # Counts hashtags and outputs the top
 hashtag_dictionary = {x: 0 for x in hashtags}
 for hashtag in hashtags:
     hashtag_dictionary[hashtag] += 1
-
 hashtag_dictionary = dict(sorted(hashtag_dictionary.items(), key=lambda item: item[1], reverse=True))
 print("===================")
 print("Top 10 #hashtags:")
@@ -48,10 +52,10 @@ with open("AFINN-111.txt", "r", encoding="utf-8") as AFINNdict:
     for line in AFINNdict:
         words = nltk.word_tokenize(line)
         nr = words[len(words) - 1]
-        str = ""
+        strn = ""
         for x in range(len(words) - 1):
-            str += words[x]
-        word_emotion_dict[str] = nr
+            strn += words[x]
+        word_emotion_dict[strn] = nr
 
 for id in words_per_tweet:
     total_rating = 0
@@ -59,7 +63,7 @@ for id in words_per_tweet:
         if word.lower() in word_emotion_dict:
             total_rating += int(word_emotion_dict[word.lower()])
     tweet_rated_emotion[id] = total_rating
-    
+
 print("==========================")
 print("Top 10 Positive :D Tweets:")
 print("==========================")
@@ -82,3 +86,37 @@ print("=====================================")
 print("All Tweets Rated by Emotional Damage:")
 print("=====================================")
 print(tweet_rated_emotion)
+
+# Creates the CSV file
+studentID = 10
+startingPoint = studentID * int(200/7)
+endingPoint = startingPoint + 200
+graph_dict = {}
+maxm = 0
+for i in range(startingPoint, endingPoint):
+    for x in wordsForCSV[i]:
+        graph_dict[x] = []
+filter_words = ["RT"]
+file = open("data.csv", "w", encoding="utf-8")
+file.write("NODE,")
+for i in range(startingPoint, endingPoint):
+    for word in wordsForCSV[i]:
+        for x in wordsForCSV[i]:
+            if x is not word and x not in graph_dict[word] and x not in filter_words:
+                graph_dict[word].append(x)
+for x in graph_dict:
+    if len(graph_dict[x]) > maxm:
+        maxm = len(graph_dict[x])
+for x in range(maxm):
+    file.write("EDGE" + str(x))
+    if x != maxm - 1:
+        file.write(",")
+file.write("\n")
+for x in graph_dict:
+    file.write(x)
+    file.write(",")
+    for z in range(len(graph_dict[x])):
+        file.write(graph_dict[x][z])
+        if z != len(graph_dict[x]) - 1:
+            file.write(",")
+    file.write("\n")