Update app.py

app.py

@@ -1,11 +1,60 @@
 import streamlit as st
 import difflib
 import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+import plotly.express as px
+import warnings
+warnings.filterwarnings("ignore")
+%matplotlib inline
+
+
+# for text data preprocessing
+import re
+from nltk.corpus import stopwords
+from nltk.stem.porter import PorterStemmer
+from wordcloud import WordCloud
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
 
 # Assuming you have 'lpi_df' and 'similarity' defined before this point
 
 lpi_df = pd.read_csv('Learning_Pathway_Index.csv')
 
+lpi_df['combined_features'] = lpi_df['Course_Learning_Material']+' '+lpi_df['Source']+' '+lpi_df['Course_Level']+' '+lpi_df['Type']+' '+lpi_df['Module']+' '+lpi_df['Difficulty_Level']+' '+lpi_df['Keywords_Tags_Skills_Interests_Categories']
+
+combined_features = lpi_df['combined_features']
+
+porter_stemmer = PorterStemmer()
+
+
+def stemming(content):
+    stemmed_content = re.sub('[^a-zA-Z]',' ',content)
+    stemmed_content = stemmed_content.lower()
+    stemmed_content = stemmed_content.split()
+    stemmed_content = [porter_stemmer.stem(word) for word in stemmed_content if not word in stopwords.words('english')]
+    stemmed_content = ' '.join(stemmed_content)
+    return stemmed_content
+
+combined_features = combined_features.apply(stemming)
+
+
+vectorizer = TfidfVectorizer()
+
+vectorizer.fit(combined_features)
+
+combined_features = vectorizer.transform(combined_features)
+
+similarity = cosine_similarity(combined_features)
+
+
+
+
+
+
+
+
 
 st.title('Course Recommendation App')