Update app.py

app.py

@@ -1,216 +1,135 @@
-import traceback
 import gradio as gr
-import pandas as pd
-import joblib
 import re
+import joblib
+import csv
+import os
 from huggingface_hub import hf_hub_download
+from datasets import load_dataset, Dataset, concatenate_datasets
+from huggingface_hub import HfApi, HfFolder
+import pandas as pd
 
-# ---- CONFIG ----
-MODEL_REPO = "SleepyTerr/entrepreneurial_readiness"
-MODEL_FILENAME = "readiness_model.joblib"
-
-# ---- LOAD MODEL ----
-model = None
-model_load_error = None
-try:
-    model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILENAME, repo_type="model")
-    model = joblib.load(model_path)
-    print("✅ Model loaded from:", model_path)
-except Exception as e:
-    model_load_error = traceback.format_exc()
-    print("⚠️ Model load error:\n", model_load_error)
-
-# ---- Parsing ----
-def parse_input_for_fields(text):
-    text = text.lower()
-    extracted = {}
-
-    def grab(patterns, key, cast_float=True):
-        if key in extracted:
-            return
-        for pat in patterns:
-            m = re.search(pat, text)
-            if m:
-                try:
-                    extracted[key] = float(m.group(1)) if cast_float else m.group(1)
-                except:
-                    extracted[key] = m.group(1)
-                return
-
-    # Age
-    grab([
-        r"\b(\d{1,2})\s*(?:yo|yrs?|years? old)\b",
-        r"(?:i am|i'm)\s*(\d{1,2})\b",
-        r"\bage\s*(\d{1,2})\b"
-    ], "age")
-
-    # Income
-    grab([r"(?:income|earn|salary|make).{0,15}\$?(\d{3,6})"], "monthly_income")
-
-    # Expenses
-    grab([r"(?:expense|bill|spend).{0,15}\$?(\d{3,6})"], "monthly_expenses")
-
-    # Entertainment
-    grab([
-        r"(?:entertainment|fun|leisure).{0,15}\$?(\d{2,5})",
-        r"spend.{0,10}\$?(\d{2,5}).{0,10}(?:entertainment|fun|leisure)"
-    ], "entertainment_spending")
-
-    # Savings
-    grab([r"(?:savings|saved).{0,15}\$?(\d{3,7})"], "savings_amount")
-
-    # Assets
-    grab([r"(?:asset|net worth|property).{0,15}\$?(\d{3,8})"], "assets")
-
-    # Risk tolerance
-    grab([r"(?:risk).{0,15}(\d{1,2})"], "risk_tolerance_1_10")
-
-    # Sales skills
-    grab([r"(?:sales|selling).{0,15}(\d{1,2})"], "sales_skills_1_5")
-
-    # Dependents → support "no kids"/"none"
-    if any(phrase in text for phrase in ["no kids", "none", "0 dependents"]):
-        extracted["dependence_1_5"] = 0
-    else:
-        grab([r"(?:dependents?|kids|children).{0,15}(\d{1,2})"], "dependence_1_5")
-
-    return extracted
-
-# ---- Compute numeric score ----
-def compute_readiness(row):
-    score = 0
-    score += row.get("risk_tolerance_1_10", 0) * 2
-    score += row.get("sales_skills_1_5", 0) * 4
-
-    disposable = row.get("monthly_income", 0) - row.get("monthly_expenses", 0)
-    if disposable > 0:
-        score += disposable / 200
-    else:
-        score += disposable / 500
-
-    score += row.get("savings_amount", 0) / 2000
-    score += row.get("assets", 0) / 20000
-    score -= row.get("dependence_1_5", 0) * 3
-
-    return min(max(score, 0), 100)
-
-# ---- Conversation state ----
-conversation_state = {"collected": {}}
-
-REQUIRED_FIELDS = [
-    "age",
-    "monthly_income",
-    "monthly_expenses",
-    "entertainment_spending",
-    "savings_amount",
-    "assets",
-    "risk_tolerance_1_10",
-    "sales_skills_1_5",
-    "dependence_1_5"
-]
-
-def chatbot(user_input, history):
+DATASET_REPO = "SleepyTerr/entrepreneurial_readiness_v2"
+
+# Load model
+model_repo_id = "SleepyTerr/entrepreneurial_readiness"
+model_file = hf_hub_download(repo_id=model_repo_id, filename="readiness_model.joblib", repo_type="model")
+model = joblib.load(model_file)
+
+# Conversation state
+expected_fields = ["age", "risk_tolerance", "sales_skills", "dependents", 
+                   "monthly_income", "monthly_expenses", "entertainment", 
+                   "savings", "assets"]
+
+field_questions = {
+    "age": "How old are you?",
+    "risk_tolerance": "On a scale of 1-10, how much risk are you willing to take?",
+    "sales_skills": "On a scale of 1-10, how would you rate your sales skills?",
+    "dependents": "How many dependents do you take care of?",
+    "monthly_income": "What is your monthly income?",
+    "monthly_expenses": "What are your monthly expenses?",
+    "entertainment": "How much do you spend on entertainment each month?",
+    "savings": "How much do you currently have saved?",
+    "assets": "What is the total value of your assets?"
+}
+
+def parse_info(message):
+    """Extract possible numbers from free text"""
+    numbers = re.findall(r"\d+", message)
+    return [int(n) for n in numbers]
+
+def generate_tips(user_data, score):
+    """Give personalized tips depending on weaknesses"""
+    tips = []
+    if user_data.get("monthly_expenses", 0) > user_data.get("monthly_income", 0) * 0.8:
+        tips.append("Try to lower your expenses so they don’t eat up most of your income.")
+    if user_data.get("savings", 0) < user_data.get("monthly_income", 0) * 2:
+        tips.append("Build an emergency fund with at least 2–3 months of income saved.")
+    if user_data.get("assets", 0) < user_data.get("monthly_income", 0) * 6:
+        tips.append("Work on building long-term assets to increase stability.")
+    if user_data.get("sales_skills", 0) < 5:
+        tips.append("Consider improving your sales or communication skills—they’re key for entrepreneurship.")
+    if user_data.get("risk_tolerance", 0) < 4:
+        tips.append("Think about whether you’re comfortable taking risks—entrepreneurship often involves uncertainty.")
+    
+    if not tips:
+        tips.append("Great job! You’re on a strong path to entrepreneurship.")
+    
+    return tips
+
+def save_to_db(user_data, score):
     try:
-        collected = conversation_state["collected"]
-
-        # Parse free-text
-        new_data = parse_input_for_fields(user_input)
-        for k, v in new_data.items():
-            if k not in collected:
-                collected[k] = v
-
-        # Check missing
-        missing = [f for f in REQUIRED_FIELDS if f not in collected]
-        if missing:
-            field_map = {
-                "age": "your age (just the number)",
-                "monthly_income": "your monthly income ($, just numbers)",
-                "monthly_expenses": "your monthly expenses ($)",
-                "entertainment_spending": "your monthly entertainment spending ($)",
-                "savings_amount": "your savings ($)",
-                "assets": "your assets/net worth ($)",
-                "risk_tolerance_1_10": "your risk tolerance (1–10)",
-                "sales_skills_1_5": "your sales skills (1–5)",
-                "dependence_1_5": "how many dependents you support (number or 'none')"
-            }
-            next_field = missing[0]
-
-            # If user typed only a number in response
-            if re.fullmatch(r"\d+", user_input.strip()):
-                collected[next_field] = float(user_input.strip())
-                missing = [f for f in REQUIRED_FIELDS if f not in collected]
-                if not missing:
-                    # All done
-                    df = pd.DataFrame([collected])
-                    label = None
-                    try:
-                        if model:
-                            raw_pred = model.predict(df)
-                            label = raw_pred[0] if hasattr(raw_pred, "__len__") else raw_pred
-                    except Exception:
-                        label = None
-
-                    score = compute_readiness(collected)
-                    conversation_state["collected"] = {}
-
-                    response = f"📊 Your entrepreneurial readiness score is **{score:.1f}/100**."
-                    if label:
-                        response += f" The model also classified you as: **{label}**."
-                    return response
-
-            return f"Hmm... I think I need a bit more info. Could you tell me {field_map[next_field]}?"
-
-        # All info collected
-        df = pd.DataFrame([collected])
-        label = None
-        try:
-            if model:
-                raw_pred = model.predict(df)
-                label = raw_pred[0] if hasattr(raw_pred, "__len__") else raw_pred
-        except Exception:
-            label = None
-
-        score = compute_readiness(collected)
-        conversation_state["collected"] = {}
-
-        response = f"📊 Your entrepreneurial readiness score is **{score:.1f}/100**."
-        if label:
-            response += f" The model also classified you as: **{label}**."
-
-        return response
-
-    except Exception:
-        return "⚠️ Error in chatbot:\n" + traceback.format_exc()
-
-# ---- Gradio UI ----
-with gr.Blocks(theme=gr.themes.Soft(primary_hue="purple", secondary_hue="purple")) as demo:
-    gr.Markdown(
-        """
-        <h1 style='text-align:center; color:#D8B4FE;'>💬 Entrepreneurial Readiness Chatbot</h1>
-        <p style='text-align:center; color:#E9D5FF; font-size:16px;'>
-        👋 Hello! I'm an <b>entrepreneurial readiness chatbot</b>.<br>
-        Tell me a little about yourself (e.g., age, income, expenses, savings, etc.)<br>
-        and I'll give you a readiness score between 0 and 100!
-        </p>
-        """,
-    )
-
-    chatbot_ui = gr.ChatInterface(
-        fn=chatbot,
-        chatbot=gr.Chatbot(
-            height=450,
-            bubble_full_width=False,
-            show_copy_button=True,
-        ),
-        textbox=gr.Textbox(
-            placeholder="Type your scenario here...",
-            container=True,
-        ),
-        title="Entrepreneurial Readiness Chatbot",
-        description="I’ll guide you step by step if I need more info."
-    )
-
-if model_load_error:
-    print("=== MODEL LOAD ERROR ===\n", model_load_error)
+        # Convert to pandas row
+        row = {**user_data, "score": score}
+        df = pd.DataFrame([row])
+
+        # Load existing dataset
+        ds = load_dataset(DATASET_REPO, split="train")
+
+        # Convert new row into a Dataset
+        new_ds = Dataset.from_pandas(df)
+
+        # Concatenate
+        updated = concatenate_datasets([ds, new_ds])
+
+        # Push back to Hugging Face
+        updated.push_to_hub(DATASET_REPO, split="train")
+
+        print("✅ Response saved to Hugging Face dataset")
+    except Exception as e:
+        print("⚠️ Failed to save:", e)
+
+def chatbot(message, history, user_data, current_field):
+    history = history or []
+    user_data = user_data or {}
+    current_field = current_field or expected_fields[0]
+
+    # If current field not filled, try to extract it
+    if current_field in expected_fields:
+        nums = parse_info(message)
+        if nums:
+            user_data[current_field] = nums[0]
+            # Move to next field
+            next_index = expected_fields.index(current_field) + 1
+            if next_index < len(expected_fields):
+                current_field = expected_fields[next_index]
+                history.append((message, field_questions[current_field]))
+            else:
+                # All info collected → make prediction
+                features = [user_data.get(f, 0) for f in expected_fields]
+                score = model.predict([features])[0]
+                tips = generate_tips(user_data, score)
+                tips_text = "\n- " + "\n- ".join(tips)
+
+                # Save to database (CSV here, but can be swapped)
+                save_to_db(user_data, score)
+
+                history.append((message, f"✅ Your entrepreneurial readiness score is **{score:.1f}/100**!\n\nHere are some tips to improve:\n{tips_text}"))
+                return history, user_data, None
+        else:
+            # Ask again in case of missing number
+            history.append((message, f"Please provide a number for {current_field}."))
+    else:
+        history.append((message, "Hmm... I need a bit more info. Can you clarify?"))
+
+    return history, user_data, current_field
+
+with gr.Blocks(css="""
+    body {background-color: #1a002b;}
+    .chatbot {background-color: #2d0a45; border-radius: 12px; padding: 10px;}
+    .message.user {background-color: #5a2d82; color: white; border-radius: 8px; padding: 8px; margin: 5px;}
+    .message.bot {background-color: #3b0f58; color: #eee; border-radius: 8px; padding: 8px; margin: 5px;}
+""") as demo:
+    gr.Markdown("<h1 style='color:white; text-align:center;'>💡 Entrepreneurial Readiness Chatbot</h1>")
+    gr.Markdown("<p style='color:#ddd; text-align:center;'>Hello! I'm an entrepreneurial readiness chatbot! 🧑‍💻<br>Tell me a little about yourself and I'll give you a score between 0 and 100!</p>")
+    
+    chatbot_ui = gr.Chatbot(label="Chat", elem_classes="chatbot", height=400)
+    msg = gr.Textbox(placeholder="Type your scenario here...", label="Your Message")
+    state = gr.State({})
+    current_field = gr.State(expected_fields[0])
+
+    def respond(message, history, user_data, current_field):
+        return chatbot(message, history, user_data, current_field)
+
+    msg.submit(respond, [msg, chatbot_ui, state, current_field], [chatbot_ui, state, current_field])
 
 demo.launch()