Update app.py

app.py

@@ -2,38 +2,37 @@ import streamlit as st
 import difflib
 import pandas as pd
 import numpy as np
-
-
-# for text data preprocessing
 import re
 import nltk
-nltk.download('stopwords')
 from nltk.corpus import stopwords
 from nltk.stem.porter import PorterStemmer
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 
+# Download NLTK stopwords if not already done
+nltk.download('stopwords')
 
+# Read the data
 lpi_df = pd.read_csv('Learning Pathway Index.csv')
 
-lpi_df.rename(columns={"Course / Learning material": "Course_Learning_Material",
-                       "Course Level": "Course_Level",
-                       "Type (Free or Paid)":"Type",
-                       "Module / Sub-module \nDifficulty level": "Difficulty_Level",
-                       "Keywords / Tags / Skills / Interests / Categories":"Keywords"
-                      }, inplace=True)
-
-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']
-
+# Rename columns
+lpi_df.rename(columns={
+    "Course / Learning material": "Course_Learning_Material",
+    "Course Level": "Course_Level",
+    "Type (Free or Paid)": "Type",
+    "Module / Sub-module \nDifficulty level": "Difficulty_Level",
+    "Keywords / Tags / Skills / Interests / Categories": "Keywords"
+}, inplace=True)
 
+# Combine features
+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']
 
+# Text preprocessing
 combined_features = lpi_df['combined_features']
-
 porter_stemmer = PorterStemmer()
 
-
 def stemming(content):
-    stemmed_content = re.sub('[^a-zA-Z]',' ',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')]
@@ -42,20 +41,20 @@ def stemming(content):
 
 combined_features = combined_features.apply(stemming)
 
-
+# TF-IDF and similarity
 vectorizer = TfidfVectorizer()
-
 vectorizer.fit(combined_features)
-
 combined_features = vectorizer.transform(combined_features)
-
 similarity = cosine_similarity(combined_features)
 
-
-
+# Streamlit app
+st.set_page_config(
+    page_title="Course Recommendation App",
+    page_icon="✅",
+    layout="wide",
+)
 
 st.title('Learning Pathway Index Course Recommendation')
-
 user_input = st.text_input('Enter What You Want to Learn : ')
 
 if user_input:
@@ -68,18 +67,20 @@ if user_input:
         similarity_score = list(enumerate(similarity[index_of_the_course]))
         sorted_similar_course = sorted(similarity_score, key=lambda x: x[1], reverse=True)
 
-        st.write('Courses suggested for you :')
-
-        i = 1
-        for course in sorted_similar_course:
-            index = course[0]
-            title_from_index = lpi_df[lpi_df.index == index]['Module'].values[0]
-            if i < 30:
-                st.write(f"{i}. {title_from_index}")
-                i += 1
-
-        if i == 1:
-            st.write('No close matches found.')
+        st.subheader('Courses suggested for you:')
+        with st.beta_container():
+            col1, col2 = st.beta_columns(2)
+            for i, course in enumerate(sorted_similar_course[:30], start=1):
+                index = course[0]
+                title_from_index = lpi_df.loc[index, 'Module']
+                if i % 2 == 0:
+                    with col2:
+                        st.write(f"{i}. {title_from_index}")
+                else:
+                    with col1:
+                        st.write(f"{i}. {title_from_index}")
+
+        if len(sorted_similar_course) == 0:
+            st.warning('No close matches found.')
     else:
-        st.write('No close matches found.')
-
+        st.warning('No close matches found.')