Update app.py

app.py

@@ -0,0 +1,134 @@
+import streamlit as st
+import pandas as pd
+import pymongo
+from sentence_transformers import SentenceTransformer
+import numpy as np
+from sklearn.feature_extraction.text import TfidfVectorizer
+import pickle
+import os
+from datetime import datetime
+
+# MongoDB Connection
+MONGO_URI = "mongodb://muhammadbinimran1001:[email protected]:27017,dsm-shard-00-01.inrzs.mongodb.net:27017,dsm-shard-00-02.inrzs.mongodb.net:27017/?ssl=true&replicaSet=atlas-nbg4er-shard-0&authSource=admin&retryWrites=true&w=majority"
+client = pymongo.MongoClient(MONGO_URI)
+db = client['test']
+users_collection = db['users']
+jobs_collection = db['jobs']
+courses_collection = db['courses']
+
+# Load Datasets
+@st.cache_data
+def load_data():
+    questions_df = pd.read_csv("Generated_Skill-Based_Questions.csv")
+    jobs_df = pd.read_csv("Updated_Job_Posting_Dataset.csv")
+    courses_df = pd.read_csv("coursera_course_dataset_v2_no_null.csv")
+    return questions_df, jobs_df, courses_df
+
+questions_df, jobs_df, courses_df = load_data()
+
+# Load or Initialize Model
+@st.cache_resource
+def load_model():
+    return SentenceTransformer('all-MiniLM-L6-v2')
+
+model = load_model()
+tfidf_vectorizer = TfidfVectorizer(stop_words='english')
+
+# Skill Extraction and Question Generation
+def get_user_skills(user_id):
+    user = users_collection.find_one({"_id": user_id})
+    return user.get("skills", []) if user else []
+
+def get_questions_for_skills(skills):
+    questions = []
+    for skill in skills:
+        skill_questions = questions_df[questions_df['Skill'] == skill].sample(1)
+        if not skill_questions.empty:
+            questions.append(skill_questions.iloc[0])
+    return pd.DataFrame(questions) if questions else None
+
+# Answer Evaluation
+def evaluate_answer(user_answer, expected_answer):
+    user_embedding = model.encode([user_answer], convert_to_tensor=True)[0]
+    expected_embedding = model.encode([expected_answer], convert_to_tensor=True)[0]
+    score = util.pytorch_cos_sim(user_embedding, expected_embedding).item() * 100
+    return max(0, round(score, 2))
+
+# Recommendation Logic
+def recommend_courses(skills, user_level):
+    skill_indices = [questions_df.index[questions_df['Skill'] == skill].tolist()[0] for skill in skills if skill in questions_df['Skill'].values]
+    if not skill_indices:
+        return []
+    course_skills = courses_df['skills'].fillna("").tolist()
+    course_embeddings = model.encode(course_skills, convert_to_tensor=True)
+    skill_embeddings = model.encode(skills, convert_to_tensor=True)
+    similarities = util.pytorch_cos_sim(skill_embeddings, course_embeddings).cpu().numpy()
+    total_scores = 0.6 * np.max(similarities, axis=0)
+    idx = np.argsort(-total_scores)[:3]
+    return courses_df.iloc[idx][['course_title', 'Organization']].values.tolist()
+
+def recommend_jobs(skills, user_level):
+    skill_indices = [questions_df.index[questions_df['Skill'] == skill].tolist()[0] for skill in skills if skill in questions_df['Skill'].values]
+    if not skill_indices:
+        return []
+    job_skills = jobs_df['required_skills'].fillna("").tolist()
+    job_embeddings = model.encode(job_skills, convert_to_tensor=True)
+    skill_embeddings = model.encode(skills, convert_to_tensor=True)
+    similarities = util.pytorch_cos_sim(skill_embeddings, job_embeddings).cpu().numpy()
+    total_scores = 0.5 * np.max(similarities, axis=0)
+    idx = np.argsort(-total_scores)[:3]
+    return jobs_df.iloc[idx][['job_title', 'company_name', 'location']].values.tolist()
+
+# Streamlit App
+st.title("Skill Assessment & Recommendation")
+
+# Simulate User Signup (for demo, replace with actual auth)
+if 'user_id' not in st.session_state:
+    st.session_state.user_id = "68233a6b7c0fd8f9d6994e"  # Example user ID
+    st.session_state.skills = get_user_skills(st.session_state.user_id)
+    st.session_state.scores = {}
+
+if not st.session_state.skills:
+    st.write("No skills found. Please update your profile with skills during signup.")
+else:
+    st.write(f"Detected Skills: {st.session_state.skills}")
+
+    if 'questions' not in st.session_state:
+        st.session_state.questions = get_questions_for_skills(st.session_state.skills)
+        if st.session_state.questions is not None:
+            st.session_state.questions = st.session_state.questions.reset_index(drop=True)
+
+    if st.session_state.questions is not None and not st.session_state.questions.empty:
+        for idx, row in st.session_state.questions.iterrows():
+            st.subheader(f"Question for {row['Skill']}")
+            user_answer = st.text_area(f"Question: {row['Question']}", key=f"answer_{idx}")
+            if st.button(f"Submit Answer for {row['Skill']}", key=f"submit_{idx}"):
+                score = evaluate_answer(user_answer, row['Answer'])
+                st.session_state.scores[row['Skill']] = score
+                st.success(f"Score for {row['Skill']}: {score}%")
+
+        if all(skill in st.session_state.scores for skill in st.session_state.skills):
+            st.write("Assessment Complete!")
+            mean_score = np.mean(list(st.session_state.scores.values()))
+            weak_skills = [s for s, score in st.session_state.scores.items() if score < 60]
+            st.write(f"Mean Score: {mean_score:.2f}%")
+            st.write(f"Weak Skills: {weak_skills}")
+
+            courses = recommend_courses(weak_skills or st.session_state.skills, "Intermediate")
+            jobs = recommend_jobs(st.session_state.skills, "Intermediate")
+            st.write("Recommended Courses:", courses)
+            st.write("Recommended Jobs:", jobs)
+
+            # Update user score in MongoDB (simplified)
+            users_collection.update_one(
+                {"_id": st.session_state.user_id},
+                {"$set": {"skills_scores": st.session_state.scores}}
+            )
+            st.session_state.pop('questions', None)
+    else:
+        st.write("No questions available for the detected skills.")
+
+# Redirect to Dashboard (simulated)
+if st.button("Go to Dashboard"):
+    st.write("Redirecting to User Dashboard...")
+    # In a real app, use st.experimental_rerun() or a navigation library