hugging

.devcontainer/devcontainer.json

@@ -0,0 +1,33 @@
+{
+  "name": "Python 3",
+  // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+  "image": "mcr.microsoft.com/devcontainers/python:1-3.11-bullseye",
+  "customizations": {
+    "codespaces": {
+      "openFiles": [
+        "README.md",
+        "app.py"
+      ]
+    },
+    "vscode": {
+      "settings": {},
+      "extensions": [
+        "ms-python.python",
+        "ms-python.vscode-pylance"
+      ]
+    }
+  },
+  "updateContentCommand": "[ -f packages.txt ] && sudo apt update && sudo apt upgrade -y && sudo xargs apt install -y <packages.txt; [ -f requirements.txt ] && pip3 install --user -r requirements.txt; pip3 install --user streamlit; echo '✅ Packages installed and Requirements met'",
+  "postAttachCommand": {
+    "server": "streamlit run app.py --server.enableCORS false --server.enableXsrfProtection false"
+  },
+  "portsAttributes": {
+    "8501": {
+      "label": "Application",
+      "onAutoForward": "openPreview"
+    }
+  },
+  "forwardPorts": [
+    8501
+  ]
+}

.gitattributes

@@ -33,4 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-data/raw_data/Data.csv filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -4,4 +4,4 @@ __pycache__/
 *.pyo
 
 # Ignore CSV's present in raw_data folder
-*.env
+*/raw_data

README.md

@@ -1,8 +1,8 @@
 ---
 title: VayuBuddy Question And Answer
 emoji: 🚀
-colorFrom: yellow
-colorTo: green
+colorFrom: pink
+colorTo: red
 sdk: streamlit
 sdk_version: 1.42.0
 app_file: app.py

app.py

@@ -1,10 +1,6 @@
 import streamlit as st
-from utils.save_to_hf import commit_and_push_changes  
 
 st.set_page_config(page_title="Coding Questions App", layout="wide")
 st.title("Welcome to the Coding Questions App!")
 
 st.write("Use the sidebar to navigate between pages.")
-
-if st.sidebar.button("Save to HF"):
-    commit_and_push_changes()

data/questions/2/answer.txt

@@ -1 +0,0 @@
-Andhra Pradesh

data/questions/2/code.py

@@ -1,10 +0,0 @@
-def true_code():
-    import pandas as pd
-    
-    df = pd.read_csv('data/raw_data/Data.csv', sep=",")
-    
-    data = df[df['PM2.5'] > 300]
-    ans = data.groupby(['state', 'station']).value_counts().idxmax()[0]
-    print(ans)
-
-true_code()

data/questions/2/metadata.json

@@ -1,9 +0,0 @@
-{
-    "question_id": 2,
-    "category": "spatial",
-    "answer_category": "single",
-    "plot": false,
-    "libraries": [
-        "pandas"
-    ]
-}

data/questions/2/question.txt

@@ -1 +0,0 @@
-Which state had the most days with hazardous PM2.5 levels (above 300 µg/m³)?

data/questions/3/answer.txt

@@ -1,3 +0,0 @@
-Winter Average PM2.5: 67.4923443634478
-Monsoon Average PM2.5: 34.42519611317571
-Summer Average PM2.5: nan

data/questions/3/code.py

@@ -1,25 +0,0 @@
-def true_code():
-    import pandas as pd
-    
-    df = pd.read_csv('data/raw_data/Data.csv', sep=",")
-    
-    df['Timestamp'] = pd.to_datetime(df['Timestamp'])
-    df['Year'] = df['Timestamp'].dt.year
-    df['Month'] = df['Timestamp'].dt.month
-    
-    data = df[df['Year'] == 2018]
-    data = data[data['station'] == 'Lal Bahadur Shastri Nagar, Kalaburagi - KSPCB']
-    
-    winter_data = data[(data['Month'] == 12) | (data['Month'] <= 2)]
-    summer_data = data[(data['Month'] >= 3) & (data['Month'] <= 5)]
-    monsoon_data = data[(data['Month'] >= 6) & (data['Month'] <= 9)]
-    
-    summer_avg = summer_data['PM2.5'].mean()
-    winter_avg = winter_data['PM2.5'].mean()
-    monsoon_avg = monsoon_data['PM2.5'].mean()
-    
-    print("Winter Average PM2.5:", winter_avg)
-    print("Monsoon Average PM2.5:", monsoon_avg)
-    print("Summer Average PM2.5:", summer_avg)
-
-true_code()

data/questions/3/metadata.json

@@ -1,9 +0,0 @@
-{
-    "question_id": 3,
-    "category": "temporal",
-    "answer_category": "multiple",
-    "plot": false,
-    "libraries": [
-        "pandas"
-    ]
-}

data/questions/3/question.txt

@@ -1 +0,0 @@
-For the year 2018, calculate the average PM2.5 concentration for each season (Winter: December-February, Summer: March-May, and Monsoon: June-September) for station Lal Bahadur Shastri Nagar, Kalaburagi - KSPCB. Identify the season with the highest pollution and suggest potential factors contributing to the increase.

data/raw_data/Data.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:77ea5aff6c41f6e8e5562a75ec4ac97f498debd706d3a047e1b57a9d8bd42be1
-size 266893056

data/raw_data/NCAP_Funding.csv

@@ -1,118 +0,0 @@
-S. No.,State,City,Amount released during FY 2019-20,Amount released during FY 2020-21,Amount released during FY 2021-22,Total fund released,Utilisation as on June 2022
-1,Andhra Pradesh,Vijaywada,6,-,-,6,22.91
-2,Andhra Pradesh,Guntur,0.12,0.76,1.96,2.84,22.91
-3,Andhra Pradesh,Kurnool,0.06,0.76,1.36,2.18,22.91
-4,Andhra Pradesh,Nellore,0.06,0.76,1.92,2.74,22.91
-5,Andhra Pradesh,Visakhapatnam,0.12,-,-,0.12,22.91
-6,Andhra Pradesh,Srikakulam,-,2,0.49,2.49,22.91
-7,Andhra Pradesh,Chitoor,-,2,0.46,2.46,22.91
-8,Andhra Pradesh,Ongole,-,2,0.64,2.64,22.91
-9,Andhra Pradesh,vizianagaram,-,2,0.83,2.83,22.91
-10,Andhra Pradesh,Eluru,-,2,0.82,2.82,22.91
-11,Andhra Pradesh,Rajahmundry,-,2,1.13,3.13,22.91
-12,Andhra Pradesh,Anantapur,-,2,1.04,3.04,22.91
-13,Andhra Pradesh,Kadapa,-,1,0.83,1.83,22.91
-14,Assam,Guwahati,0.12,5,-,5.12,1.45
-15,Assam,Nagaon,0.06,2,-,2.06,1.45
-16,Assam,Nalbari,0.06,1,-,1.06,1.45
-17,Assam,Sibsagar,0.06,2,-,2.06,1.45
-18,Assam,Silchar,0.06,2,-,2.06,1.45
-19,Bihar,Patna,10,-,-,10,15.2
-20,Bihar,Gaya,0.1,2,1.9,4,15.2
-21,Bihar,Muzaffarpur,0.1,5,2.5,7.6,15.2
-22,Chandigarh,Chandigarh,8.28,5,4.61,17.89,10.83
-23,Chhattisgarh,Raipur,6,-,-,6,2.76
-24,Chhattisgarh,Durg Bhilainagar,6,-,-,6,2.76
-25,Chhattisgarh,Korba,0.06,1,-,1.06,2.76
-26,Delhi,Delhi,-,-,11.25,11.25,-
-27,Gujarat,Surat,6,-,-,6,12
-28,Gujarat,Ahmedabad,6,-,-,6,12
-29,Himachal Pradesh,Baddi (Baddi&nalagarh considered twin during FY 20-21),0.06,3,0.2,3.26,6.35
-30,Himachal Pradesh,Nalagarh,0.06,-,0.06,0.12,6.35
-31,Himachal Pradesh,Paonta Sahib,0.06,1,0.1,1.16,6.35
-32,Himachal Pradesh,Sunder Nagar,0.06,1,0.08,1.14,6.35
-33,Himachal Pradesh,Kala Amb,-,3,0,3,6.35
-34,Himachal Pradesh,Damtal,-,1,0.01,1.01,6.35
-35,Himachal Pradesh,Parwanoo,-,1,0.03,1.03,6.35
-36,Jammu & Kashmir,Jammu,0.12,3,4.89,8.01,0.12
-37,Jammu & Kashmir,Srinagar,-,5,7.95,12.95,0.12
-38,Jharkhand,Dhanbad,6,-,-,6,3
-39,Karnataka,Bangalore,6,-,-,6,7.39
-40,Karnataka,Gulburga,0.12,0.38,2.24,2.74,7.39
-41,Karnataka,Hubli-Dharwad,0.12,0.38,3.68,4.18,7.39
-42,Karnataka,Devangere,0.06,0.76,1.4,2.22,7.39
-43,Madhya Pradesh,Bhopal,10,-,-,10,20.96
-44,Madhya Pradesh,Gwalior,10,-,-,10,20.96
-45,Madhya Pradesh,Indore,0.2,-,-,0.2,20.96
-46,Madhya Pradesh,Ujjain,0.2,0.38,2.33,2.91,20.96
-47,Madhya Pradesh,Sagar,0.1,0.76,1.36,2.22,20.96
-48,Madhya Pradesh,Dewas,0.1,0.38,1.33,1.81,20.96
-49,Maharashtra,Mumbai,9.5,-,-,9.5,29.92
-50,Maharashtra,Nagpur,9.45,-,-,9.45,29.92
-51,Maharashtra,Navi Mumbai,9.45,-,-,9.45,29.92
-52,Maharashtra,Pune,9.45,-,-,9.45,29.92
-53,Maharashtra,Amravati,0.2,1.14,2.91,4.25,29.92
-54,Maharashtra,Aurangabad,0.2,-,-,0.2,29.92
-55,Maharashtra,Nashik,0.2,-,-,0.2,29.92
-56,Maharashtra,Kolhapur,0.2,0.76,-,0.96,29.92
-57,Maharashtra,Sangli,0.2,0.76,1.72,2.68,29.92
-58,Maharashtra,Solapur,0.2,0.38,4.2,4.78,29.92
-59,Maharashtra,Ulhasnagar,0.2,1.9,-,2.1,29.92
-60,Maharashtra,Akola,0.1,1.14,1.47,2.71,29.92
-61,Maharashtra,Badlapur,0.1,1.9,-,2,29.92
-62,Maharashtra,Chandrapur,0.1,1.14,-,1.24,29.92
-63,Maharashtra,Jalgaon,0.1,0.76,-,0.86,29.92
-64,Maharashtra,Jalna,0.1,1.14,-,1.24,29.92
-65,Maharashtra,Latur,0.1,0.38,1.6,2.08,29.92
-66,Meghalaya,Byrnihat,-,3,0,3,1.97
-67,Nagaland,Dimapur,0.06,3,0.53,3.59,6.12
-68,Nagaland,Kohima,0.06,3,0.4,3.46,6.12
-69,Odisha,Twin City Bhubaneshwar & Cuttack,6,-,-,6,3.62
-70,Odisha,Balasore,0.06,0.76,-,0.82,3.62
-71,Odisha,Rourkela,0.06,1.14,-,1.2,3.62
-72,Odisha,Angul,0.06,1.14,-,1.2,3.62
-73,Odisha,Kalinga Nagar,-,3,-,3,3.62
-74,Odisha,Talcher,-,-,0.22,0.22,3.62
-75,Odisha,Cuttack,-,-,3.42,3.42,3.62
-76,Punjab,Ludhiana,6,-,-,6,3.02
-77,Punjab,Amritsar,6,-,-,6,3.02
-78,Punjab,Jalandhar,0.12,4,-,4.12,3.02
-79,Punjab,Khanna,0.06,1.9,-,1.96,3.02
-80,Punjab,Gobindgarh,0.06,3,-,3.06,3.02
-81,Punjab,NayaNangal,0.06,1,-,1.06,3.02
-82,Punjab,Dera Baba Nanak,0.06,0.76,-,0.82,3.02
-83,Punjab,Patiala,0.06,4,-,4.06,3.02
-84,Punjab,DeraBassi,0.06,0.38,-,0.44,3.02
-85,Rajasthan,Jaipur,6,-,-,6,12.55
-86,Rajasthan,Jodhpur,6,-,-,6,12.55
-87,Rajasthan,Kota,6,-,-,6,12.55
-88,Rajasthan,Alwar,0.06,1.9,-,1.96,12.55
-89,Rajasthan,Udaipur,0.06,1.9,-,1.96,12.55
-90,Tamil Nadu,Tuticorin,0.06,3,-,3.06,-
-91,Telangana,Hyderabad,10.8,-,-,10.8,9.72
-92,Telangana,Nalgonda,0.1,0.38,0.47,0.95,9.72
-93,Telangana,Patencheru,0.1,0.38,-,0.48,9.72
-94,Telangana,Sangareddy,-,2,0.32,2.32,9.72
-95,Uttar Pradesh,Agra,9.45,-,-,9.45,30.57
-96,Uttar Pradesh,Allahabad,9.45,-,-,9.45,30.57
-97,Uttar Pradesh,Kanpur,9.45,-,-,9.45,30.57
-98,Uttar Pradesh,Lucknow,9.45,-,-,9.45,30.57
-99,Uttar Pradesh,Varanasi,9.47,-,-,9.47,30.57
-100,Uttar Pradesh,Moradabad,0.2,1.9,-,2.1,30.57
-101,Uttar Pradesh,Bareily,0.2,1.9,-,2.1,30.57
-102,Uttar Pradesh,Firozabad,0.2,1.9,-,2.1,30.57
-103,Uttar Pradesh,Jhansi,0.2,1.14,-,1.34,30.57
-104,Uttar Pradesh,Khurja,0.1,1.9,-,2,30.57
-105,Uttar Pradesh,Anpara,0.1,1.14,-,1.24,30.57
-106,Uttar Pradesh,Gajraula,0.1,1.14,-,1.24,30.57
-107,Uttar Pradesh,Raebareli,0.1,1.14,-,1.24,30.57
-108,Uttar Pradesh,Gorakhpur,-,-,9.64,9.64,30.57
-109,Uttar Pradesh,Noida,-,-,6.67,6.67,30.57
-110,Uttarakhand,Kashipur,0.06,3,0.79,3.85,8.15
-111,Uttarakhand,Rishikesh,0.06,5,-,5.06,8.15
-112,Uttarakhand,Dehradun,-,3,4.88,7.88,8.15
-113,West Bengal,Kolkata,6,-,-,6,19
-114,West Bengal,Howrah,-,5,-,5,19
-115,West Bengal,Haldia,-,3,-,3,19
-116,West Bengal,Durgapur,-,3,-,3,19
-117,West Bengal,Barrackpore,-,2,-,2,19

data/raw_data/State_data.csv

@@ -1,32 +0,0 @@
-State,Population,Area (km2)
-Uttar Pradesh,199812341,240928
-Maharashtra,112374333,307713
-Bihar,104099452,94163
-West Bengal,91276115,88752
-Madhya Pradesh,72626809,308252
-Tamil Nadu,72147030,130058
-Rajasthan,68548437,342239
-Karnataka,61095297,191791
-Gujarat,60439692,196024
-Andhra Pradesh,49577103,162975
-Odisha,41974219,155707
-Telangana,35003674,112077
-Kerala,33406061,38863
-Jharkhand,32988134,79716
-Assam,31205576,78438
-Punjab,27743338,50362
-Chhattisgarh,25545198,135192
-Delhi,16787941,1484
-Haryana,25351462,44212
-Jammu and Kashmir,12267032,42241
-Uttarakhand,10086292,53483
-Himachal Pradesh,6864602,55673
-Tripura,3673917,10491
-Manipur,2570390,22327
-Meghalaya,2966889,22429
-Nagaland,1978502,16579
-Arunachal Pradesh,1383727,83743
-Puducherry,1247953,479
-Mizoram,1097206,21081
-Chandigarh,1055450,114
-Sikkim,610577,7096

output.jsonl

@@ -1 +1,2 @@
-{"folder": 3, "question": "For the year 2018, calculate the average PM2.5 concentration for each season (Winter: December-February, Summer: March-May, and Monsoon: June-September) for station Lal Bahadur Shastri Nagar, Kalaburagi - KSPCB. Identify the season with the highest pollution and suggest potential factors contributing to the increase.", "answer": "Winter Average PM2.5: 67.4923443634478\nMonsoon Average PM2.5: 34.42519611317571\nSummer Average PM2.5: nan", "code": "def true_code():\n    import pandas as pd\n    \n    df = pd.read_csv('data/raw_data/Data.csv', sep=\",\")\n    \n    df['Timestamp'] = pd.to_datetime(df['Timestamp'])\n    df['Year'] = df['Timestamp'].dt.year\n    df['Month'] = df['Timestamp'].dt.month\n    \n    data = df[df['Year'] == 2018]\n    data = data[data['station'] == 'Lal Bahadur Shastri Nagar, Kalaburagi - KSPCB']\n    \n    winter_data = data[(data['Month'] == 12) | (data['Month'] <= 2)]\n    summer_data = data[(data['Month'] >= 3) & (data['Month'] <= 5)]\n    monsoon_data = data[(data['Month'] >= 6) & (data['Month'] <= 9)]\n    \n    summer_avg = summer_data['PM2.5'].mean()\n    winter_avg = winter_data['PM2.5'].mean()\n    monsoon_avg = monsoon_data['PM2.5'].mean()\n    \n    print(\"Winter Average PM2.5:\", winter_avg)\n    print(\"Monsoon Average PM2.5:\", monsoon_avg)\n    print(\"Summer Average PM2.5:\", summer_avg)\n\ntrue_code()", "metadata": {"question_id": 3, "category": "temporal", "answer_category": "multiple", "plot": false, "libraries": ["pandas"]}}
+{"folder": "0", "question": "Which state has the highest average PM2.5 concentration across all stations?", "answer": "Delhi", "code": "def true_code():\n    import pandas as pd\n    \n    df = pd.read_csv('data/raw_data/Data.csv', sep=\",\")\n    \n    data = df.groupby(['state','station'])['PM2.5'].mean()\n    ans = data.idxmax()[0]\n    print(ans)\n\ntrue_code()", "metadata": {"question_id": 0, "category": "spatial", "answer_category": "single", "plot": false, "libraries": ["pandas"]}}
+{"folder": "1", "question": "Report the station that recorded the highest value of PM 2.5 for the month Aug of 2020", "answer": "Lal Bahadur Shastri Nagar, Kalaburagi ", "code": "def true_code():\n    import pandas as pd\n    \n    df = pd.read_csv('data/raw_data/Data.csv', sep=\",\")\n    \n    df['Timestamp'] = pd.to_datetime(df['Timestamp'])\n    \n    df['Year'] = df['Timestamp'].dt.year\n    df['Month'] = df['Timestamp'].dt.month\n    data = df[(df['Year'] == 2020) & (df['Month'] == 8)]\n    ans = data.groupby('station')['PM2.5'].max().idxmax()\n    print(ans)\n\ntrue_code()", "metadata": {"question_id": 2, "category": "temporal", "answer_category": "double", "plot": false, "libraries": ["pandas"]}}

pages/3_Add_Questions.py

@@ -52,17 +52,6 @@ if st.button("Save Question"):
             with open(question_dir / "metadata.json", "w", encoding="utf-8") as f:
                 json.dump(metadata, f, indent=4)
 
-            new_entry = {
-                "folder": question_id,
-                "question": question_text,
-                "answer": answer_text,
-                "code": formatted_code,
-                "metadata": metadata
-            }
-
-            with open ("output.jsonl", "a", encoding="utf-8") as f:
-                f.write(json.dumps(new_entry, ensure_ascii=False) + "\n")
-
             st.success(f"✅ Question saved successfully! (ID: {question_id})")
             st.info("refresh in-order to see the applied changes")
             if st.button("refresh") :

pages/5_Delete_Question.py

@@ -62,7 +62,7 @@ if selected_question:
             question_folder = DATA_DIR / str(selected_question_id)
             if question_folder.exists():
                 shutil.rmtree(question_folder)  
-                rename_folders(selected_question_id)
+                rename_folders(selected_question_id) 
                 st.success(f"✅ Question ID {selected_question_id} deleted successfully!")
                 st.info("Refresh to see the applied changes")
                 if st.button("Refresh"):

utils/save_to_hf.py

@@ -1,34 +0,0 @@
-def commit_and_push_changes():
-    import os
-    import subprocess
-    from pathlib import Path
-
-    # Define the paths
-    REPO_DIR = Path(".")  # Root directory of your Hugging Face Space repo
-    DATA_DIR = REPO_DIR / "data/questions"  # Persistent storage in the repo
-    JSONL_FILE = REPO_DIR / "output.jsonl"
-
-    DATA_DIR.mkdir(parents=True, exist_ok=True)  # Ensure directory exists
-
-    GIT_USER = os.getenv("GIT_USER")
-    GIT_EMAIL = os.getenv("GIT_EMAIL")
-    HF_OWNER = os.getenv("HF_OWNER")
-    HF_TOKEN = os.getenv("HF_TOKEN")
-    REPO_NAME = os.getenv("REPO_NAME")
-    REPO_URL = f"https://{HF_OWNER}:{HF_TOKEN}@huggingface.co/spaces/{REPO_NAME}"
-
-    # Set remote URL before pushing
-
-    """Automates Git add, commit, and push for updated data."""
-    try:
-        # Run Git commands
-        subprocess.run(["git", "config", "--global", "user.name", GIT_USER], check=True)
-        subprocess.run(["git", "config", "--global", "user.email", GIT_EMAIL], check=True)
-        subprocess.run(["git", "remote", "set-url", "origin", REPO_URL], check=True)
-        subprocess.run(["git", "add", "--all"], check=True)
-        subprocess.run(["git", "commit", "-m", "Update questions data"], check=True)
-        subprocess.run(["git", "push", "origin", "main"], check=True)
-        print("✅ Data committed and pushed successfully!")
-    
-    except subprocess.CalledProcessError as e:
-        print(f"❌ Git operation failed: {e}")