diff --git a/0509_lda.jl b/0509_lda.jl
new file mode 100644
index 0000000..acf2fef
Binary files /dev/null and b/0509_lda.jl differ
diff --git a/text_analysis/topicModel.py b/text_analysis/topicModel.py
index 91677c0..bb00598 100644
--- a/text_analysis/topicModel.py
+++ b/text_analysis/topicModel.py
@@ -5,6 +5,7 @@ import glob
 import copy
 from statistics import mean, median
 from strip_markdown import strip_markdown
+import joblib
 
 from getMetadata import metadata_for_file
 
@@ -35,6 +36,7 @@ def get_data_from_dir(directory):
     data_list = []
     word_counts = []
     avg_word_lengths = []
+    file_list = []
     for file in files:
         text = open(file, encoding='utf-8').read()
         #here's some of the descriptive text analysis
@@ -43,7 +45,9 @@ def get_data_from_dir(directory):
         avg_word_lengths.append(avg_word_length)
         #adding the data to the list of text
         data_list.append(text)
-    return data_list, word_counts, avg_word_lengths
+        #adding filename
+        file_list.append(file)
+    return data_list, word_counts, avg_word_lengths, file_list
 
 #preprocessing text data
 def preprocess(corpus_list):
@@ -103,18 +107,29 @@ def best_lda_model(data_vectorized, vocab):
         print('Topic: %d' % topic)
         print('  %s' % ', '.join(words))
     #lda.print_topics(num_words=10)
+    joblib.dump(lda, '0509_lda.jl')
+    #lda = joblib.load('0509_lda.jl')
+    return id_topic
 
-
+def get_most_prevalent(distributions, documents):
+    most_prevalent = {0: [0, ""],1: [0, ""], 2: [0, ""], 3: [0, ""], 4: [0, ""], 5: [0, ""], 6: [0, ""],  7: [0, ""]}
+    for i, topic_distribution in enumerate(distributions):
+        for j in range(8):
+            if topic_distribution[j] > most_prevalent[j][0]:
+                most_prevalent[j] = [topic_distribution[j], documents[i]]
+    print(most_prevalent)
+    return most_prevalent
 
 if __name__ == "__main__":
     readme_directory = "/data/users/mgaughan/kkex/time_specific_files/readme2"
     contributing_directory = "/data/users/mgaughan/kkex/time_specific_files/contributing2"
-    listed_corpus, wordcounts, wordlengths = get_data_from_dir(readme_directory)
+    listed_corpus, wordcounts, wordlengths, file_list = get_data_from_dir(readme_directory)
     print("Mean wordcount: ", mean(wordcounts))
     print("Median wordcount: ", median(wordcounts))
     print("Mean wordlength: ", mean(wordlengths))
     print("Median wordlength: ", median(wordlengths))
     lemmatized_corpus = preprocess(listed_corpus)
+    #print(lemmatized_corpus)
     #prepped_corpus, id2word = text_preparation(lemmatized_corpus)
     vectorizer = CountVectorizer(analyzer='word',       
                              min_df=2,                        
@@ -122,11 +137,13 @@ if __name__ == "__main__":
                              lowercase=True,                   
                              token_pattern='[a-zA-Z0-9]{2,}',  
                             )
-    data_vectorized = vectorizer.fit_transform(lemmatized_corpus)                        
+    data_vectorized = vectorizer.fit_transform(lemmatized_corpus)    
+    #print(data_vectorized)                    
     #lda_model_identification(data_vectorized)
     #freqs = zip(vectorizer.get_feature_names_out(), data_vectorized.sum(axis=0).tolist()[0])    
     # sort from largest to smallest
     #print(sorted(freqs, key=lambda x: -x[1])[:25])
-    best_lda_model(data_vectorized, vectorizer.get_feature_names_out())
+    topic_distributions = best_lda_model(data_vectorized, vectorizer.get_feature_names_out())
+    get_most_prevalent(topic_distributions, file_list)