Upload 3 files

Dockerfile

@@ -0,0 +1,15 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD uvicorn main:app --port=8000 --host=0.0.0.0
+

main.py

@@ -0,0 +1,147 @@
+from fastapi import FastAPI, HTTPException
+import gspread
+from google.oauth2.service_account import Credentials
+from google.auth.exceptions import GoogleAuthError
+import pandas as pd
+from collections import defaultdict
+from pydantic import BaseModel
+from fastapi.middleware.cors import CORSMiddleware
+import os
+
+app = FastAPI()
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # You can specify domains instead of "*" to restrict access
+    allow_credentials=True,
+    allow_methods=["*"],  # Allows all HTTP methods (POST, GET, OPTIONS, etc.)
+    allow_headers=["*"],  # Allows all headers
+)
+# Define Google Sheets API credentials function
+def get_credentials():
+    try:
+        service_account_info = {
+            "type": os.getenv("SERVICE_ACCOUNT_TYPE"),
+            "project_id": os.getenv("PROJECT_ID"),
+            "private_key_id": os.getenv("PRIVATE_KEY_ID"),
+            "private_key": os.getenv("PRIVATE_KEY").replace('\\n', '\n'),
+            "client_email": os.getenv("CLIENT_EMAIL"),
+            "client_id": os.getenv("CLIENT_ID"),
+            "auth_uri": os.getenv("AUTH_URI"),
+            "token_uri": os.getenv("TOKEN_URI"),
+            "auth_provider_x509_cert_url": os.getenv("AUTH_PROVIDER_X509_CERT_URL"),
+            "client_x509_cert_url": os.getenv("CLIENT_X509_CERT_URL"),
+            "universe_domain": os.getenv("UNIVERSE_DOMAIN")
+        }
+        scope = ['https://spreadsheets.google.com/feeds', 'https://www.googleapis.com/auth/drive']
+        creds = Credentials.from_service_account_info(service_account_info, scopes=scope)
+        return creds
+    except Exception as e:
+        print(f"Error getting credentials: {e}")
+        return None
+
+# Initialize Google Sheets Client
+creds = get_credentials()
+if creds:
+    client = gspread.authorize(creds)
+
+# Define input model
+class CoachingCodeInput(BaseModel):
+    coachingCode: str
+
+# Define the endpoint
+@app.post("/process/")
+def process_data(input_data: CoachingCodeInput):
+    coachingCode = input_data.coachingCode
+
+    # Define Google Sheet URLs based on coachingCode
+    journal_file_path = ''
+    panic_button_file_path = ''
+    test_file_path = ''
+
+    if coachingCode == '1919':
+        journal_file_path = 'https://docs.google.com/spreadsheets/d/1EFf2lr4A10nt4RhIqxCD_fxe-l3sXH09II0TEkMmvhA/edit?usp=drive_link'
+        panic_button_file_path = 'https://docs.google.com/spreadsheets/d/1nFZGkCvRV6qS-mhsORhX3dxI0JSge32_UwWgWKl3eyw/edit?usp=drive_link'
+        test_file_path = 'https://docs.google.com/spreadsheets/d/13PUHySUXWtKBusjugoe7Dbsm39PwBUfG4tGLipspIx4/edit?usp=drive_link'
+    else:
+        raise HTTPException(status_code=404, detail="Invalid coaching code")
+
+    try:
+        # Open the Google Sheets
+        journal_file = client.open_by_url(journal_file_path).worksheet('Sheet1')
+        panic_button_file = client.open_by_url(panic_button_file_path).worksheet('Sheet1')
+        test_file = client.open_by_url(test_file_path).worksheet('Sheet1')
+
+        # Step 1: Read the Google Sheets into DataFrames
+        journal_df = pd.DataFrame(journal_file.get_all_values())
+        panic_button_df = pd.DataFrame(panic_button_file.get_all_values())
+        test_df = pd.DataFrame(test_file.get_all_values())
+
+        # Label the columns manually
+        journal_df.columns = ['user_id', 'productivity_yes_no', 'productivity_rate']
+        panic_button_df.columns = ['user_id', 'panic_button']
+
+        # Step 2: Merge Journal and Panic Button data
+        panic_button_grouped = panic_button_df.groupby('user_id')['panic_button'].apply(lambda x: ','.join(x)).reset_index()
+        merged_journal_panic = pd.merge(journal_df, panic_button_grouped, on='user_id', how='outer')
+
+        # Step 3: Process Test data
+        test_data = []
+        for index, row in test_df.iterrows():
+            user_id = row[0]
+            i = 1
+            while i < len(row) and pd.notna(row[i]):
+                chapter = row[i].lower().strip()
+                score = row[i + 1]
+                if pd.notna(score):
+                    test_data.append({'user_id': user_id, 'test_chapter': chapter, 'test_score': score})
+                i += 2
+
+        test_df_processed = pd.DataFrame(test_data)
+
+        # Step 4: Merge all data
+        merged_data = pd.merge(merged_journal_panic, test_df_processed, on='user_id', how='outer')
+        merged_data_cleaned = merged_data.dropna(subset=['productivity_yes_no', 'productivity_rate', 'panic_button', 'test_chapter'], how='all')
+
+        # Step 5: Process Data
+        df = pd.DataFrame(merged_data_cleaned)
+        academic_weights = {'BACKLOGS': -5, 'MISSED CLASSES': -4, 'NOT UNDERSTANDING': -3, 'BAD MARKS': -3, 'LACK OF MOTIVATION': -3}
+        non_academic_weights = {'EMOTIONAL FACTORS': -3, 'PROCRASTINATE': -2, 'LOST INTEREST': -4, 'LACK OF FOCUS': -2, 'GOALS NOT ACHIEVED': -2, 'LACK OF DISCIPLINE': -2}
+        max_weighted_panic_score = sum([max(academic_weights.values()) * 3, max(non_academic_weights.values()) * 3])
+
+        def calculate_potential_score(row):
+            test_score_normalized = 0
+            if row['test_scores']:
+                avg_test_score = sum(row['test_scores'].values()) / len(row['test_scores'])
+                test_score_normalized = (avg_test_score / 40) * 70
+
+            student_panic_score = 0
+            if row['panic_button']:
+                for factor, count in row['panic_button'].items():
+                    if factor in academic_weights:
+                        student_panic_score += academic_weights[factor] * count
+                    elif factor in non_academic_weights:
+                        student_panic_score += non_academic_weights[factor] * count
+
+            panic_score = 20 * (1 - (student_panic_score / max_weighted_panic_score)) if max_weighted_panic_score != 0 else 1
+            journal_score = (float(row['productivity_rate']) / 10) * 10 if pd.notna(row['productivity_rate']) else 0
+
+            total_potential_score = test_score_normalized + panic_score + journal_score
+            return total_potential_score
+
+        merged_df = df.groupby('user_id').apply(lambda group: pd.Series({
+            'potential_score': calculate_potential_score(group)
+        })).reset_index()
+
+        merged_df['potential_score'] = merged_df['potential_score'].round(2)
+        sorted_df = merged_df[['user_id', 'potential_score']].sort_values(by='potential_score', ascending=False)
+
+        # Return the result as JSON
+        return sorted_df.to_dict(orient='records')
+
+    except GoogleAuthError as e:
+        raise HTTPException(status_code=500, detail=f"Authentication failed: {str(e)}")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error processing data: {str(e)}")
+
+# To run the app:
+# uvicorn filename:app --reload