New data format support (pandas.DataFrame)

pyproject.toml

@@ -5,6 +5,7 @@ build-backend = "hatchling.build"
 [project]
 name = "revisitpy"
 version = "2.3.0"
+requires-python = ">=3.10"
 dependencies = [
     "anywidget",
     "pydantic>=2.10.5",

scripts/test_script.ipynb

@@ -34,7 +34,7 @@
     "\n",
     "# Now you can import your package\n",
     "import src.revisitpy.revisitpy as rvt\n",
-    "import revisit_server as rs"
+    "# import revisit_server as rs"
    ]
   },
   {
@@ -170,11 +170,192 @@
     "w = rvt.widget(study, server=True, pathToLib='/Users/bbollen23/revisit-py/.venv/lib/python3.12/site-packages/revisit_server')\n",
     "w"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test Dataframe support "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>b1</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>a</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>b</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>d</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>e</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id b1\n",
+       "0   1  a\n",
+       "1   2  b\n",
+       "2   3  C\n",
+       "3   4  d\n",
+       "4   5  e"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.DataFrame({\n",
+    "    'id': [i for i in range(1, 6)],\n",
+    "    'b1': ['a', 'b', 'C', 'd', 'e']\n",
+    "})\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[DataRow(id=1, b1='a'),\n",
+       " DataRow(id=2, b1='b'),\n",
+       " DataRow(id=3, b1='C'),\n",
+       " DataRow(id=4, b1='d'),\n",
+       " DataRow(id=5, b1='e')]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data_rows = rvt.data(df)\n",
+    "data_rows"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\n",
+      "    \"components\": [\n",
+      "        \"test_component\"\n",
+      "    ],\n",
+      "    \"order\": \"fixed\"\n",
+      "}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Test using it with from_data()\n",
+    "# it's ok if we don't have the actual md file, just need a non-empty path \n",
+    "test_component = rvt.component(\n",
+    "    type='markdown', \n",
+    "    component_name__='test_component', \n",
+    "    path='./assets/introduction.md'\n",
+    ")\n",
+    "\n",
+    "test_sequence = rvt.sequence(order='fixed', components=[test_component])\n",
+    "print(test_sequence)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\n",
+      "    \"components\": [\n",
+      "        \"test_component_id:1_b1:a\",\n",
+      "        \"test_component_id:2_b1:b\",\n",
+      "        \"test_component_id:3_b1:C\",\n",
+      "        \"test_component_id:4_b1:d\",\n",
+      "        \"test_component_id:5_b1:e\"\n",
+      "    ],\n",
+      "    \"order\": \"fixed\"\n",
+      "}\n"
+     ]
+    }
+   ],
+   "source": [
+    "test_sequence.from_data(data_rows)\n",
+    "print(test_sequence)"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -188,9 +369,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.5"
+   "version": "3.13.5"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

src/revisitpy/revisitpy.py

@@ -2,7 +2,7 @@
 import json
 from . import models as rvt_models
 from pydantic import BaseModel, ValidationError  # type: ignore
-from typing import List, Literal, get_origin, Optional, get_args, Any, Unpack, overload, get_type_hints
+from typing import List, Literal, get_origin, Optional, get_args, Any, Unpack, overload, get_type_hints, Union
 from enum import Enum
 import csv
 from dataclasses import make_dataclass, asdict
@@ -11,7 +11,10 @@
 import shutil
 from . import widget as _widget
 import inspect
-
+try:
+    import pandas as pd
+except ImportError: 
+    pd = None 
 
 __all__ = [
     "component",
@@ -547,8 +550,29 @@ def studyConfig(**kwargs: Unpack[_StudyConfigType]) -> _WrappedStudyConfig:
 
 
 # Function to parse the CSV and dynamically create data classes
-def data(file_path: str) -> List[Any]:
-    # Read the first row to get the headers
+def data(source: Union[str, "pd.DataFrame"]) -> List[Any]:
+    """
+    Parse data from. various sources into a list of DataRow objects 
+
+    Supports: 
+    - CSV file path (strings)
+    - pandas DataFrames 
+
+    Args: 
+        source 
+    """
+    if isinstance(source, str):
+        return _data_from_csv(source)
+    elif pd is not None and isinstance(source, pd.DataFrame): 
+        return _data_from_pandas(source)
+    else: 
+        raise RevisitError(
+            message=f"Unsupported data source type: {type(source)}. Use CSV file path (str), pandas DataFrame, or Polars DataFrame"
+        )
+
+
+def _data_from_csv(file_path: str) -> List[Any]:
+        # Read the first row to get the headers
     with open(file_path, mode='r') as csvfile:
         csv_reader = csv.DictReader(csvfile)
         headers = csv_reader.fieldnames
@@ -568,6 +592,20 @@ def data(file_path: str) -> List[Any]:
 
     return data_rows
 
+def _data_from_pandas(df: pd.DataFrame) -> List[Any]:
+    """Convert pandas DataFrame to list of DataRow objects."""
+    if df.empty:
+        raise RevisitError(message="DataFrame is empty.")
+
+    headers = df.columns.tolist()
+    DataRow = make_dataclass("DataRow", [(header, Any) for header in headers])
+    data_rows = []
+
+    # Convert to dict records in one shot - much faster than iterrows
+    records = df.to_dict('records')
+    data_rows = [DataRow(**record) for record in records]
+
+    return data_rows
 
 def widget(study: _WrappedStudyConfig, revisitPath: str = '', server=False, pathToLib=''):
 

tests/test_dataframe_support.py

@@ -0,0 +1,28 @@
+import pandas as pd
+import sys
+sys.path.insert(0, '/Users/shenglong/Downloads/revisitpy/src')
+
+from revisitpy import data
+
+# Test 1: CSV file
+print("Test 1: CSV file")
+csv_data = data("tests/config.json")  # Replace with actual CSV
+print(f"✓ CSV loaded: {len(csv_data)} rows")
+
+# Test 2: Pandas DataFrame
+print("\nTest 2: Pandas DataFrame")
+df = pd.DataFrame({
+    'id': [1, 2, 3],
+    'b1': [0.32, 1.2, 0.6],
+    'b2': [0.01, 1.2, 1.1]
+})
+df_data = data(df)
+print(f"✓ DataFrame loaded: {len(df_data)} rows")
+print(f"  First row: {df_data[0]}")
+
+# Test 3: Error handling
+print("\nTest 3: Error handling")
+try:
+    data(123)  # Should fail
+except Exception as e:
+    print(f"✓ Correctly raised error: {str(e)[:50]}...")