hugging (#1)

- Add coding questions, answers, and execution functionality with Streamlit interface (1d01073c0b796d69120055724e6a0c5ca088c54b)
- added requirements.txt and fix metadata file naming in jsonl_to_data.py (6cc1added742aac02303bd7d92c50e608de8e82b)
- Update README with project structure and usage instructions (9c39c7406da380f9b43dcc0634922492fd61e9e8)
- Enhance README with project aim and improve step formatting (540f8c38ae94600fa2fd823aec2e99cedb79e718)
- Added numpy to requirements.txt (de393af7eac98b07bae746f1832cfbf197cc57d4)
- Update requirements.txt (e4f095b4fed0eba14a5ff2b57cc86053e99563b0)
- Update app.py (265eba24cea7930b5b5d25cd109f601cd36df36d)
- Added Dev Container Folder (c7679f36c20723e122425c65559975836c42f17c)
- Remove pandas installation from app.py and add pandas, numpy, and streamlit to requirements.txt (5fb70820417f4794e37d0e6957339ab40bb65fd1)
- Add .gitattributes for LFS tracking and update README with new app metadata (23f90200c1f572a4890cefeaadced2d019d80f03)
- Merge branch 'main' of https://huggingface.co/spaces/ratneshpasi03/VayuBuddy-Question-and-Answer into pr/1 (c450fac6f8290e57bdb6e431f994f548f2070253)

.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
+  ]
+}

.gitignore

@@ -0,0 +1,7 @@
+# Ignore Python cache files
+__pycache__/
+*.pyc
+*.pyo
+
+# Ignore CSV's present in raw_data folder
+*/raw_data

README.md

@@ -8,6 +8,4 @@ sdk_version: 1.42.0
 app_file: app.py
 pinned: false
 short_description: This is a streamlit app to create the collection of Question
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---

app.py

@@ -0,0 +1,6 @@
+import streamlit as st
+
+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.")

data/questions/0/answer.txt

@@ -0,0 +1 @@
+Delhi

data/questions/0/code.py

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

data/questions/0/metadata.json

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

data/questions/0/question.txt

@@ -0,0 +1 @@
+Which state has the highest average PM2.5 concentration across all stations?

data/questions/1/answer.txt

@@ -0,0 +1 @@
+Lal Bahadur Shastri Nagar, Kalaburagi 

data/questions/1/code.py

@@ -0,0 +1,14 @@
+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'] == 2020) & (df['Month'] == 8)]
+    ans = data.groupby('station')['PM2.5'].max().idxmax()
+    print(ans)
+
+true_code()

data/questions/1/metadata.json

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

data/questions/1/question.txt

@@ -0,0 +1 @@
+Report the station that recorded the highest value of PM 2.5 for the month Aug of 2020

output.jsonl

@@ -0,0 +1,2 @@
+{"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/1_All_Questions.py

@@ -0,0 +1,21 @@
+import streamlit as st
+from utils.load_jsonl import load_data
+
+# Load Data
+data_file = "output.jsonl"
+data = load_data(data_file)
+
+# Create category-wise dictionary
+category_dict = {}
+for entry in data:
+    category = entry["metadata"].get("category", "Uncategorized")
+    if category not in category_dict:
+        category_dict[category] = []
+    category_dict[category].append(entry)
+
+st.title("Questions by Category")
+
+for category, questions in category_dict.items():
+    st.subheader(category)
+    for q in questions:
+        st.write(f"🔹 {q['question']}")

pages/2_Execute_codes.py

@@ -0,0 +1,50 @@
+import subprocess
+import streamlit as st
+from utils.load_jsonl import load_data
+
+# Load Data
+data_file = "output.jsonl"
+data = load_data(data_file)
+
+# Create category-wise dictionary
+category_dict = {}
+for entry in data:
+    category = entry["metadata"].get("category", "Uncategorized")
+    if category not in category_dict:
+        category_dict[category] = []
+    category_dict[category].append(entry)
+
+st.title("Code Execution")
+
+# Select Category
+category_selected = st.selectbox("Select Category", list(category_dict.keys()))
+
+# Select Question
+question_dict = {q["question"]: {"code": q["code"], "folder": q["folder"]} for q in category_dict[category_selected]}
+question_selected = st.selectbox("Select Question", list(question_dict.keys()))
+
+# Get folder name and code snippet
+selected_entry = question_dict[question_selected]
+folder_name = selected_entry["folder"]
+code_snippet = selected_entry["code"]
+
+# Show Code Snippet
+st.code(code_snippet, language="python")
+
+# Execute Button
+if st.button("Execute"):
+    # Path to the selected code.py file
+    # code_path = script_dir.parent / "data/questions" / folder_name / "code.py"
+    code_path = f"data/questions/{folder_name}/code.py"
+
+    try:
+        # Execute the Python script and capture the output
+        result = subprocess.check_output(["python", str(code_path)], text=True, stderr=subprocess.STDOUT)
+
+        # Display the execution output
+        st.subheader("Execution Output:")
+        st.success(result)
+
+    except subprocess.CalledProcessError as e:
+        # Display any errors if execution fails
+        st.error(f"Error executing script:\n{e.output}")

pages/3_Add_Questions.py

@@ -0,0 +1,73 @@
+import streamlit as st
+import json
+from pathlib import Path
+from utils.code_services import format_code, execute_code
+
+QUESTIONS_DIR = Path("data/questions")
+QUESTIONS_DIR.mkdir(parents=True, exist_ok=True)
+
+def get_next_question_id():
+    existing_ids = [int(folder.name) for folder in QUESTIONS_DIR.iterdir() if folder.is_dir() and folder.name.isdigit()]
+    return max(existing_ids, default=-1) + 1
+
+st.title("📝 Add a New Question")
+
+question_text = st.text_area("Enter Question", placeholder="Type the question here...", height=80)
+answer_text = st.text_area("Enter Answer", placeholder="Type the answer here...", height=80)
+user_code = st.text_area("Enter Code", placeholder="Write your Python solution here...", height=300)
+
+category = st.text_input("Category", placeholder="e.g. spatial")
+answer_category = st.text_input("#### Answer Category", placeholder="e.g. signal")
+plot = st.checkbox("## Does this require a plot?")
+libraries = st.text_input("Libraries (comma-separated)", placeholder="e.g. pandas, numpy")
+
+if st.button("Save Question"):
+    if not all([question_text.strip(), answer_text.strip(), user_code.strip(), category.strip(), answer_category.strip()]):
+        st.error("❌ All fields are required. Please fill them out.")
+    else:
+        formatted_code = format_code(user_code)
+        output, error = execute_code(formatted_code)
+
+        if error:
+            st.error("❌ Code execution failed! Fix the following error before saving:")
+            st.code(error, language="plaintext")
+        else:
+            question_id = get_next_question_id()
+            question_dir = QUESTIONS_DIR / str(question_id)
+            question_dir.mkdir(parents=True, exist_ok=True)
+
+            (question_dir / "question.txt").write_text(question_text, encoding="utf-8")
+
+            (question_dir / "answer.txt").write_text(answer_text, encoding="utf-8")
+
+            (question_dir / "code.py").write_text(formatted_code, encoding="utf-8")
+
+            metadata = {
+                "question_id": question_id,
+                "category": category.strip().lower(),
+                "answer_category": answer_category.strip(),
+                "plot": plot,
+                "libraries": [lib.strip() for lib in libraries.split(",")] if libraries else []
+            }
+            with open(question_dir / "metadata.json", "w", encoding="utf-8") as f:
+                json.dump(metadata, f, indent=4)
+
+            st.success(f"✅ Question saved successfully! (ID: {question_id})")
+            st.info("refresh in-order to see the applied changes")
+            if st.button("refresh") :
+                st.rerun()
+
+if user_code:
+    st.subheader("💻 Test Your Code Before Saving")
+    formatted_test_code = format_code(user_code)
+    st.code(formatted_test_code, language="python")
+
+    if st.button("Execute Code"):
+        output, error = execute_code(formatted_test_code)
+        
+        if error:
+            st.error("❌ Code execution failed! Fix the following error:")
+            st.error(error)
+        else:
+            st.success("✅ Code executed successfully!")
+            st.success(f"Execution Output : {output}")

pages/4_Edit_Questions.py

@@ -0,0 +1,91 @@
+import json
+import streamlit as st
+from pathlib import Path
+from utils.load_jsonl import load_data
+from utils.code_services import format_code, execute_code
+
+DATA_DIR = Path("data/questions")
+JSONL_FILE = "output.jsonl"
+
+questions_data = load_data(JSONL_FILE)
+
+categories = sorted(set(q["metadata"]["category"] for q in questions_data))
+
+st.title("✏️ Edit a Question")
+
+if not categories:
+    st.warning("No categories available.")
+    st.stop()
+
+selected_category = st.selectbox("Select a Category", categories)
+
+filtered_questions = {int(q["folder"]): q["question"][:50] + "..." for q in questions_data if q["metadata"]["category"] == selected_category}
+
+if not filtered_questions:
+    st.warning("No questions found in this category.")
+    st.stop()
+
+selected_question_id = st.selectbox("Select Question to Edit", list(filtered_questions.keys()), format_func=lambda x: f"ID {x}: {filtered_questions[x]}")
+
+selected_question = next((q for q in questions_data if int(q["folder"]) == selected_question_id), None)
+
+if selected_question:
+    question_input = st.text_area("Edit Question", value=selected_question["question"])
+    answer_input = st.text_area("Edit Answer", value=selected_question["answer"])
+    code_input = st.text_area("Edit Code", value=selected_question["code"])
+
+    metadata = selected_question["metadata"]
+    category_input = st.text_input("Category", value=metadata["category"])
+    answer_category_input = st.text_input("Answer Category", value=metadata["answer_category"])
+    plot_input = st.checkbox("Does this require a plot?", value=metadata["plot"])
+    libraries_input = st.text_input("Libraries (comma-separated)", value=", ".join(metadata["libraries"]))
+
+    if st.button("Save Changes"):
+        if not all([question_input.strip(), answer_input.strip(), code_input.strip(), category_input.strip(), answer_category_input.strip()]):
+            st.error("❌ All fields are required. Please fill them out.")
+        else:
+            formatted_code = format_code(code_input)
+            output, error = execute_code(formatted_code)
+
+            if error:
+                st.error("❌ Code execution failed! Fix the following error before saving:")
+                st.code(error, language="plaintext")
+            else:
+                question_dir = DATA_DIR / str(selected_question_id)
+
+                (question_dir / "question.txt").write_text(question_input, encoding="utf-8")
+                (question_dir / "answer.txt").write_text(answer_input, encoding="utf-8")
+                (question_dir / "code.py").write_text(formatted_code, encoding="utf-8")
+
+                updated_metadata = {
+                    "question_id": selected_question_id,
+                    "category": category_input.strip(),
+                    "answer_category": answer_category_input.strip(),
+                    "plot": plot_input,
+                    "libraries": [lib.strip() for lib in libraries_input.split(",")] if libraries_input else []
+                }
+                with open(question_dir / "metadata.json", "w", encoding="utf-8") as f:
+                    json.dump(updated_metadata, f, indent=4)
+
+                st.success(f"✅ Question ID {selected_question_id} updated successfully!")
+                st.info("Refresh to see the applied changes")
+                if st.button("Refresh"):
+                    st.rerun()
+
+else:
+    st.error("❌ Failed to load question data.")
+
+if code_input:
+    st.subheader("💻 Test Your Code Before Saving")
+    formatted_test_code = format_code(code_input)
+    st.code(formatted_test_code, language="python")
+
+    if st.button("Execute Code"):
+        output, error = execute_code(formatted_test_code)
+        
+        if error:
+            st.error("❌ Code execution failed! Fix the following error:")
+            st.error(error)
+        else:
+            st.success("✅ Code executed successfully!")
+            st.success(f"Execution Output: {output}")

pages/5_Delete_Question.py

@@ -0,0 +1,74 @@
+import streamlit as st
+import os
+import shutil
+from pathlib import Path
+from utils.load_jsonl import load_data  
+
+DATA_DIR = Path("data/questions")
+JSONL_FILE = "output.jsonl"  
+
+questions_data = load_data(JSONL_FILE)
+
+categories = sorted(set(q["metadata"]["category"] for q in questions_data))
+
+st.title("🗑️ Delete a Question")
+
+if not categories:
+    st.warning("No categories available.")
+    st.stop()
+
+selected_category = st.selectbox("Select a Category", categories)
+
+filtered_questions = {int(q["folder"]): q["question"][:50] + "..." for q in questions_data if q["metadata"]["category"] == selected_category}
+
+if not filtered_questions:
+    st.warning("No questions found in this category.")
+    st.stop()
+
+selected_question_id = st.selectbox("Select Question to Delete", list(filtered_questions.keys()), format_func=lambda x: f"ID {x}: {filtered_questions[x]}")
+
+selected_question = next((q for q in questions_data if int(q["folder"]) == selected_question_id), None)
+
+if selected_question:
+    st.subheader("Question Details")
+    st.text_area("Question", value=selected_question["question"], disabled=True, height=70)
+    st.text_area("Answer", value=selected_question["answer"], disabled=True, height=70)
+
+    st.subheader("Code")
+    st.code(selected_question["code"], language="python")
+    
+    metadata = selected_question["metadata"]
+    st.subheader("Meta data")
+    st.write(f"Category : **{metadata['category']}**")
+    st.write(f"Answer Category : **{metadata['answer_category']}**")
+    st.write(f"Plot Required : **{'Yes' if metadata['plot'] else 'No'}**")
+    st.write(f"Libraries : **{', '.join(metadata['libraries']) if metadata['libraries'] else 'None'}**")
+
+    def rename_folders(deleted_id):
+        """Renames folders after deleting one to maintain continuous numbering."""
+        all_folders = sorted([int(f) for f in os.listdir(DATA_DIR) if f.isdigit()])
+        
+        for folder_id in all_folders:
+            if folder_id > deleted_id:
+                old_path = DATA_DIR / str(folder_id)
+                new_path = DATA_DIR / str(folder_id - 1)
+                shutil.move(old_path, new_path) 
+
+    st.info("Need to check the box in-order to delete the question")
+    confirm = st.checkbox("Confirm Deletion")
+    
+    if st.button("🚨 Delete This Question"):
+        if confirm:
+            question_folder = DATA_DIR / str(selected_question_id)
+            if question_folder.exists():
+                shutil.rmtree(question_folder)  
+                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"):
+                    st.rerun()
+        else:
+            st.warning("⚠️ Please check 'Confirm Deletion' before proceeding.")
+
+else:
+    st.error("❌ Failed to load question data.")

requirements.txt

@@ -0,0 +1,4 @@
+pandas
+numpy
+matplotlib
+streamlit

utils/code_services.py

@@ -0,0 +1,23 @@
+from pathlib import Path
+import os
+import subprocess
+
+def execute_code(code_content):
+    """Executes the given Python code and returns output/errors."""
+    temp_path = "temp_code.py"
+    Path(temp_path).write_text(code_content, encoding="utf-8")
+    
+    try:
+        output = subprocess.check_output(["python", temp_path], stderr=subprocess.STDOUT, text=True)
+        os.remove(temp_path)
+        return output, None
+    except subprocess.CalledProcessError as e:
+        os.remove(temp_path)
+        return None, e.output
+    
+
+def format_code(user_code):
+    if user_code.strip().startswith("def true_code()"):
+        return user_code
+    else:
+        return f"def true_code():\n    " + "\n    ".join(user_code.splitlines()) + "\n\ntrue_code()"  # Wrap in function

utils/data_to_jsonl.py

@@ -0,0 +1,47 @@
+import os
+import json
+from pathlib import Path
+
+def data_to_jsonl(input_dir, output_file):
+    """Reads data from folders inside input_dir and writes to a JSONL file."""
+    data = []
+    
+    for folder_name in sorted(os.listdir(input_dir), key=lambda x: int(x)):  # Sort numerically
+        folder_path = os.path.join(input_dir, folder_name)
+        if os.path.isdir(folder_path):  # Ensure it's a folder
+            
+            try:
+                with open(os.path.join(folder_path, "question.txt"), "r", encoding="utf-8") as f:
+                    question = f.read()
+
+                with open(os.path.join(folder_path, "answer.txt"), "r", encoding="utf-8") as f:
+                    answer = f.read()
+
+                with open(os.path.join(folder_path, "code.py"), "r", encoding="utf-8") as f:
+                    code = f.read()
+
+                with open(os.path.join(folder_path, "metadata.json"), "r", encoding="utf-8") as f:
+                    metadata = json.load(f)
+
+                data.append({
+                    "folder": folder_name,
+                    "question": question,
+                    "answer": answer,
+                    "code": code,
+                    "metadata": metadata
+                })
+            except FileNotFoundError as e:
+                print(f"Skipping {folder_name} due to missing file: {e}")
+
+    with open(output_file, "w", encoding="utf-8") as f:
+        for entry in data:
+            f.write(json.dumps(entry, ensure_ascii=False) + "\n")
+
+    print(f"Data successfully written to {output_file}")
+
+if __name__ == "__main__":
+    outputfile = input('Enter the name of file without .jsonl : ')
+
+    script_dir = Path(__file__).parent
+    input_dir = script_dir.parent / "data/questions"
+    data_to_jsonl(input_dir, f'{outputfile}.jsonl')

utils/jsonl_to_data.py

@@ -0,0 +1,32 @@
+import os
+import json
+from pathlib import Path
+
+def jsonl_to_data(input_file, output_dir):
+    """Reads a JSONL file and reconstructs the original folder structure."""
+    os.makedirs(output_dir, exist_ok=True)
+
+    with open(input_file, "r", encoding="utf-8") as f:
+        for line in f:
+            entry = json.loads(line)
+            folder_path = os.path.join(output_dir, entry["folder"])
+            os.makedirs(folder_path, exist_ok=True)
+
+            with open(os.path.join(folder_path, "question.txt"), "w", encoding="utf-8") as f_q:
+                f_q.write(entry["question"])
+
+            with open(os.path.join(folder_path, "answer.txt"), "w", encoding="utf-8") as f_a:
+                f_a.write(entry["answer"])
+
+            with open(os.path.join(folder_path, "code.py"), "w", encoding="utf-8") as f_c:
+                f_c.write(entry["code"])
+
+            with open(os.path.join(folder_path, "metadata.json"), "w", encoding="utf-8") as f_m:
+                json.dump(entry["metadata"], f_m, indent=4)
+
+    print(f"Data successfully reconstructed in {output_dir}")
+
+if __name__ == "__main__" :
+    script_dir = Path(__file__).parent
+    input_dir = script_dir.parent / "data/questions"
+    jsonl_to_data('output.jsonl', input_dir)

utils/load_jsonl.py

@@ -0,0 +1,13 @@
+import json
+from pathlib import Path
+from utils.data_to_jsonl import data_to_jsonl
+
+def load_data(jsonl_file):
+    data = []
+    script_dir = Path(__file__).parent
+    input_dir = script_dir.parent / "data/questions"
+    data_to_jsonl(input_dir, jsonl_file)
+    with open(jsonl_file, "r", encoding="utf-8") as f:
+        for line in f:
+            data.append(json.loads(line))
+    return data