Initial clean commit

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+raw_data/main_data.csv filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,12 @@
+---
+title: QandA For VayuBuddy
+emoji: 🏢
+colorFrom: purple
+colorTo: blue
+sdk: streamlit
+sdk_version: 1.42.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

add_questions.ipynb

@@ -0,0 +1,135 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import inspect\n",
+    "import subprocess\n",
+    "import numpy as np\n",
+    "import tempfile\n",
+    "from glob import glob"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Don't change this part\n",
+    "\n",
+    "You are an air quality expert Python code generator. You need to act on `data`, a pandas DataFrame with air quality data from India to answer questions about air quality. Data frequency is daily. The data has the following columns and data types: {'Timestamp': dtype('<M8[ns]'), 'station': dtype('O'), 'PM2.5': dtype('float64'), 'PM10': dtype('float64'), 'address': dtype('O'), 'city': dtype('O'), 'latitude': dtype('float64'), 'longitude': dtype('float64'), 'state': dtype('O')}."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Work on this part"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.02\n"
+     ]
+    }
+   ],
+   "source": [
+    "category = \"temporal_aggregation\"\n",
+    "question = \"What is the minimum PM2.5 value recorded ever?\"\n",
+    "\n",
+    "def true_code():\n",
+    "    import pandas as pd\n",
+    "    main_data = pd.read_csv(\"raw_data/main_data.csv\")\n",
+    "    print(main_data[\"PM2.5\"].min())\n",
+    "    \n",
+    "code = inspect.getsource(true_code) + \"\\ntrue_code()\"\n",
+    "\n",
+    "output = subprocess.check_output([\"python3\", \"-c\", code]).decode(\"utf-8\").strip()\n",
+    "print(output)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Don't change this part"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Saving to data/temporal_aggregation/jio8bxfb.json and data/temporal_aggregation/jio8bxfb.py\n"
+     ]
+    }
+   ],
+   "source": [
+    "existing_questions = []\n",
+    "existing_files = []\n",
+    "for file in glob(f\"data/*/*.json\"):\n",
+    "    with open(file, \"r\") as f:\n",
+    "        data = json.load(f)\n",
+    "        existing_questions.append(data[\"question\"])\n",
+    "        existing_files.append(file)\n",
+    "        \n",
+    "if question in existing_questions:\n",
+    "    index = existing_questions.index(question)\n",
+    "    raise ValueError(f\"Question already exists in {existing_files[index]}\")\n",
+    "\n",
+    "save_name = tempfile.mktemp(suffix='.json', prefix=\"\", dir=f\"data/{category}\")\n",
+    "save_code = save_name.replace(\".json\", \".py\")\n",
+    "print(f\"Saving to {save_name} and {save_code}\")\n",
+    "\n",
+    "with open(save_name, \"w\") as f:\n",
+    "    json_data = {\"question\": question}\n",
+    "    json.dump(json_data, f)\n",
+    "    \n",
+    "with open(save_code, \"w\") as f:\n",
+    "    f.write(code)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "zeel_py310",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

app.py

@@ -0,0 +1,51 @@
+import json
+import subprocess
+import pandas as pd
+import streamlit as st
+from glob import glob
+
+mode = st.sidebar.radio("", ["All questions", "Inspect"])
+
+
+def read_question(file):
+    with open(file, "r") as f:
+        data = json.load(f)
+    return data["question"]
+
+
+data = pd.DataFrame()
+data["file"] = glob("data/*/*.json")
+data["category"] = data["file"].apply(lambda x: " ".join(x.split("/")[1].split("_")).title())
+data["question"] = data["file"].apply(read_question)
+
+if mode == "All questions":
+    grouped_data = data.groupby("category").agg(list).reset_index()
+    for i, row in grouped_data.iterrows():
+        st.write(f"## {row['category']}")
+        for i, question in enumerate(row["question"]):
+            st.write(f"{i+1}. {question} ({row['file'][i]})")
+
+elif mode == "Inspect":
+    category = st.selectbox("Category", data["category"].unique())
+    question = st.selectbox("Question", data[data["category"] == category]["question"])
+
+    row = data[(data["category"] == category) & (data["question"] == question)].iloc[0]
+    with open(row["file"], "r") as f:
+        row_data = json.load(f)
+    with open(row["file"].replace(".json", ".py"), "r") as f:
+        row_code = f.read()
+
+    st.write(
+        f"""## Code
+```python
+{row_code}
+```
+"""
+    )
+
+    execute = st.button("Execute")
+    if execute:
+        with st.status("", expanded=True):
+            output = subprocess.check_output(["python3", row["file"].replace(".json", ".py")])
+            print(output)
+            st.write(f"{output.decode('utf-8').strip()}")

data/spatial_aggregation/se9pgd1q.json

@@ -0,0 +1 @@
+{"question": "Which city has the highest average PM2.5 in December 2023?"}

data/spatial_aggregation/se9pgd1q.py

@@ -0,0 +1,8 @@
+def true_code():
+    import pandas as pd
+    main_data = pd.read_csv("raw_data/main_data.csv")
+    main_data["Timestamp"] = pd.to_datetime(main_data["Timestamp"])
+    answer = main_data[(main_data["Timestamp"].dt.year == 2023) & (main_data["Timestamp"].dt.month == 12)].groupby("city")["PM2.5"].mean().idxmax()
+    print(answer)
+
+true_code()

data/temporal_aggregation/jio8bxfb.json

@@ -0,0 +1 @@
+{"question": "What is the minimum PM2.5 value recorded ever?"}

data/temporal_aggregation/jio8bxfb.py

@@ -0,0 +1,6 @@
+def true_code():
+    import pandas as pd
+    main_data = pd.read_csv("raw_data/main_data.csv")
+    print(main_data["PM2.5"].min())
+
+true_code()

data/temporal_aggregation/tebhtf88.json

@@ -0,0 +1 @@
+{"question": "What is the maximum PM2.5 value recorded ever?"}

data/temporal_aggregation/tebhtf88.py

@@ -0,0 +1,6 @@
+def true_code():
+    import pandas as pd
+    main_data = pd.read_csv("raw_data/main_data.csv")
+    print(main_data["PM2.5"].max())
+
+true_code()

raw_data/main_data.csv

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