Clustering code edited

cgp1/CgpApp/topicclustering.py

@@ -24,27 +24,7 @@ import json
 class TopicCluster:
 
     def cluster():
-        texts = [
-            "Registrar of Births Deaths and MarriagesAdditional Marriages Kandyan",
-            "Registrar of Muslim Marriages -Gampaha",
-            "Registrar of Births Deaths and Marriages",
-            "Registrar of Muslim Marriages -Ratnapura",
-            "Registrar of Births Deaths and MarriagesAdditional Marriages Kandyan",
-            "Teacher Services 2021 for sinhala,Tamil and English-Kaluthara District",
-            "Teacher Services 2021 for sinhala,Tamil and English-Galle District",
-            "Teacher Services for sinhala-Ratnapura District",
-            "Medical officer preliminary grade i",
-            "medical consultant",
-            "medical officer grade i",
-            "medical officer grade ii",
-            "Medical officer preliminary grade ii",
-            "Community Development Assistant",
-            "Data Processing Assistant -colombo",
-            "Community Development Assistant",
-            "Data Processing Assistant -ratnapura",
-            "Social Development Assistant",
-        ]
-
+        #clustering with k-means
         count_vectorizer = CountVectorizer()
 
         # .fit_transfer TOKENIZES and COUNTS
@@ -109,12 +89,7 @@ class TopicCluster:
         l2_df = pd.DataFrame(
             X.toarray(), columns=l2_vectorizer.get_feature_names())
         # l2_df
-
-        # Initialize a vectorizer
-        vectorizer = TfidfVectorizer(
-            use_idf=True, tokenizer=stemming_tokenizer, stop_words='english')
-        X = vectorizer.fit_transform(texts)
-
+#removing unwanted file
         # distortions = []
         # K = range(1, 8)
         # for k in K: