Create app.py

app.py

@@ -0,0 +1,74 @@
+import streamlit as st 
+import streamlit.components.v1 as stc 
+import pandas as pd 
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.metrics.pairwise import cosine_similarity,linear_kernel
+
+import re
+import pandas as pd 
+import numpy as np 
+import matplotlib.pyplot as plt 
+import neattext.functions as nfx
+from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import warnings
+st.set_page_config(layout="wide", initial_sidebar_state="expanded")
+
+warnings.filterwarnings("ignore")
+data= pd.read_csv("udemy_courses.csv")
+data["titre_OK"]= data.course_title.apply(nfx.remove_stopwords)
+data["titre_OK"]= data.course_title.apply(nfx.remove_special_characters)
+countVec= CountVectorizer()
+cv= countVec.fit_transform(data.titre_OK)
+df=data
+matrice_cosine= cosine_similarity(cv)
+
+def recommend_course2(title, numrec=10):
+    try:
+        pattern = re.compile(re.escape(title), re.IGNORECASE)
+        matching_courses = df['course_title'].apply(lambda x: bool(pattern.search(x)))    
+        index = df[matching_courses].index[0]
+        scores = list(enumerate(matrice_cosine[index]))
+        sorted_scores = sorted(scores, key=lambda x: x[1], reverse=True)
+        selected_course_index = [i[0] for i in sorted_scores[1:]]
+        selected_course_score = [i[1] for i in sorted_scores[1:]]
+        rec_df = df.iloc[selected_course_index]
+        rec_df['Similarity_Score'] = selected_course_score
+
+        final_recommended_courses = rec_df[["course_title","level", "subject","Similarity_Score"]]
+    except:
+        final_recommended_courses= pd.DataFrame({"data": "Aucune Recommendaion disponible!"},index=[0])
+        
+    return final_recommended_courses.head(numrec)
+
+
+
+def main():
+
+	st.title("Système de Recommandation de Cours")
+
+	menu = ["Accueil","Recommendations","A propos"]
+	choice = st.sidebar.selectbox("Menu",menu)
+
+
+	if choice == "Accueil":
+		st.subheader("Accueil")
+		st.dataframe(df.head(10))
+
+
+	elif choice == "Recommendations":
+		st.subheader("Recommendations de formation")
+		search_term = st.text_input("cours")
+		num_of_rec = st.sidebar.number_input("Nombre de cours",4,30,7)
+		if st.button("Recommendations"):
+			if search_term:
+				st.write(recommend_course2(search_term, num_of_rec))
+	else:
+		st.subheader("A propos")
+		st.text("Keyce @2024")
+
+
+if __name__ == '__main__':
+	main()
+
+