Feature/curioipynb - .ipynb import/export support to Curio

docs/examples/notebooks/example10-notebook.ipynb

@@ -0,0 +1,80 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "source": "__trill_node__ = {\n    \"id\": \"82537c44-8195-4cd3-a5fa-8a049d53d96e\",\n    \"type\": \"DATA_LOADING\",\n    \"in\": \"DEFAULT\",\n    \"out\": \"DEFAULT\"\n}\n\n__trill_connections__ = {\n  \"inputs\": [],\n  \"outputs\": [\n    {\n      \"source\": \"82537c44-8195-4cd3-a5fa-8a049d53d96e\",\n      \"target\": \"e5e7e21f-609d-496b-b231-659ee91ff9af\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ]\n}\n\ndef _curio_node():\n\n    import pandas as pd\n\n    df = pd.read_csv(\"data/Green_Roofs.csv\")\n    return df\n\n_curio_output = _curio_node()\n\ntry:\n    data_82537c44_8195_4cd3_a5fa_8a049d53d96e = _curio_output\nexcept NameError:\n    data_82537c44_8195_4cd3_a5fa_8a049d53d96e = None\n",
+      "metadata": {
+        "id": "82537c44-8195-4cd3-a5fa-8a049d53d96e",
+        "language": "python"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": "__trill_node__ = {\n    \"id\": \"e5e7e21f-609d-496b-b231-659ee91ff9af\",\n    \"type\": \"DATA_CLEANING\",\n    \"in\": \"DEFAULT\",\n    \"out\": \"DEFAULT\"\n}\n\n__trill_connections__ = {\n  \"inputs\": [\n    {\n      \"source\": \"82537c44-8195-4cd3-a5fa-8a049d53d96e\",\n      \"target\": \"e5e7e21f-609d-496b-b231-659ee91ff9af\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ],\n  \"outputs\": [\n    {\n      \"source\": \"e5e7e21f-609d-496b-b231-659ee91ff9af\",\n      \"target\": \"4226b7ed-c8e7-4acf-873b-2d835d9c4a07\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ]\n}\n\ndef _curio_node():\n\n    input_0 = data_82537c44_8195_4cd3_a5fa_8a049d53d96e\n    arg = input_0\n\n    import pandas as pd\n\n    df = arg\n    df.fillna(0, inplace=True)\n\n    return df\n\n\n_curio_output = _curio_node()\n\ntry:\n    result_e5e7e21f_609d_496b_b231_659ee91ff9af = _curio_output\nexcept NameError:\n    result_e5e7e21f_609d_496b_b231_659ee91ff9af = None\n",
+      "metadata": {
+        "id": "e5e7e21f-609d-496b-b231-659ee91ff9af",
+        "language": "python"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": "__trill_node__ = {\n    \"id\": \"4226b7ed-c8e7-4acf-873b-2d835d9c4a07\",\n    \"type\": \"VIS_VEGA\",\n    \"in\": \"DEFAULT\",\n    \"out\": \"DEFAULT\"\n}\n\n__trill_connections__ = {\n  \"inputs\": [\n    {\n      \"source\": \"e5e7e21f-609d-496b-b231-659ee91ff9af\",\n      \"target\": \"4226b7ed-c8e7-4acf-873b-2d835d9c4a07\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ],\n  \"outputs\": []\n}\n\ndef _curio_node():\n\n\n    input_data = result_e5e7e21f_609d_496b_b231_659ee91ff9af\n\n    spec = {\n      \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.json\",\n      \"description\": \"Histogram of Total Roof Size of Buildings in Chicago (log-scaled)\",\n      \"data\": {\n        \"name\": \"data\"\n      },\n      \"transform\": [\n        { \"filter\": \"datum.TOTAL_ROOF_SQFT > 0\" },\n        {\n          \"calculate\": \"log(datum.TOTAL_ROOF_SQFT) / log(10)\",\n          \"as\": \"log_roof_size\"\n        }\n      ],\n      \"mark\": \"bar\",\n      \"encoding\": {\n        \"x\": {\n          \"field\": \"log_roof_size\",\n          \"bin\": { \"maxbins\": 30 },\n          \"axis\": {\n            \"title\": \"Total Roof Size (sqft)\",\n            \"values\": [3, 4, 5, 6],\n            \"labelExpr\": \"'10^' + datum.value\"\n          }\n        },\n        \"y\": {\n          \"aggregate\": \"count\",\n          \"type\": \"quantitative\",\n          \"axis\": {\n            \"title\": \"Number of Buildings\"\n          }\n        }\n      }\n    }\n\n    values = input_data\n    if hasattr(input_data, \"to_dict\"):\n        values = input_data.to_dict(orient=\"records\")\n\n    if isinstance(spec, dict):\n        spec[\"data\"] = {\"values\": values}\n\n    from IPython.display import display\n    display({\"application/vnd.vegalite.v5+json\": spec, \"text/plain\": spec}, raw=True)\n\n    return input_data\n\n\n_curio_output = _curio_node()\n\ntry:\n    result_4226b7ed_c8e7_4acf_873b_2d835d9c4a07 = _curio_output\nexcept NameError:\n    result_4226b7ed_c8e7_4acf_873b_2d835d9c4a07 = None\n",
+      "metadata": {
+        "id": "4226b7ed-c8e7-4acf-873b-2d835d9c4a07",
+        "language": "python"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": "__trill_node__ = {\n    \"id\": \"92717c5a-2e65-4ca3-9818-d5f73c89f0a9\",\n    \"type\": \"DATA_LOADING\",\n    \"in\": \"DEFAULT\",\n    \"out\": \"DEFAULT\"\n}\n\n__trill_connections__ = {\n  \"inputs\": [],\n  \"outputs\": [\n    {\n      \"source\": \"92717c5a-2e65-4ca3-9818-d5f73c89f0a9\",\n      \"target\": \"c528f5bc-5d28-4c72-9158-dfb4282c504f\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ]\n}\n\ndef _curio_node():\n\n    import geopandas as gpd\n    import pandas as pd\n    from shapely.geometry import Point\n    # Read the green roofs dataset\n    green_roofs_df = pd.read_csv('data/Green_Roofs.csv')\n\n    # Create the dataset into geo dataframe using latitude and longitude columns\n    geometry = [Point(xy) for xy in zip(green_roofs_df['LONGITUDE'], green_roofs_df['LATITUDE'])]\n    green_roofs_df = gpd.GeoDataFrame(green_roofs_df, geometry=geometry, crs=4326)\n    chicago = gpd.read_file(\"data/chicago.geojson\")\n\n    # Joining the green roofs dataset with the chicago neighborhood geojson file\n    joined = gpd.sjoin(green_roofs_df, chicago, predicate='within')\n    return joined\n\n_curio_output = _curio_node()\n\ntry:\n    data_92717c5a_2e65_4ca3_9818_d5f73c89f0a9 = _curio_output\nexcept NameError:\n    data_92717c5a_2e65_4ca3_9818_d5f73c89f0a9 = None\n",
+      "metadata": {
+        "id": "92717c5a-2e65-4ca3-9818-d5f73c89f0a9",
+        "language": "python"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": "__trill_node__ = {\n    \"id\": \"c528f5bc-5d28-4c72-9158-dfb4282c504f\",\n    \"type\": \"DATA_POOL\",\n    \"in\": \"DEFAULT\",\n    \"out\": \"DEFAULT\"\n}\n\n__trill_connections__ = {\n  \"inputs\": [\n    {\n      \"source\": \"92717c5a-2e65-4ca3-9818-d5f73c89f0a9\",\n      \"target\": \"c528f5bc-5d28-4c72-9158-dfb4282c504f\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ],\n  \"outputs\": [\n    {\n      \"source\": \"c528f5bc-5d28-4c72-9158-dfb4282c504f\",\n      \"target\": \"5c11ed5f-c993-4940-89d0-08d186e903f9\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    },\n    {\n      \"source\": \"c528f5bc-5d28-4c72-9158-dfb4282c504f\",\n      \"target\": \"a9995883-f2ea-4b42-b74d-59ebc727afc6\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ]\n}\n\ndef _curio_node():\n\n\n    return data_92717c5a_2e65_4ca3_9818_d5f73c89f0a9\n\n\n_curio_output = _curio_node()\n\ntry:\n    pool_c528f5bc_5d28_4c72_9158_dfb4282c504f = _curio_output\nexcept NameError:\n    pool_c528f5bc_5d28_4c72_9158_dfb4282c504f = None\n",
+      "metadata": {
+        "id": "c528f5bc-5d28-4c72-9158-dfb4282c504f",
+        "language": "python"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": "__trill_node__ = {\n    \"id\": \"5c11ed5f-c993-4940-89d0-08d186e903f9\",\n    \"type\": \"VIS_VEGA\",\n    \"in\": \"DEFAULT\",\n    \"out\": \"DEFAULT\"\n}\n\n__trill_connections__ = {\n  \"inputs\": [\n    {\n      \"source\": \"c528f5bc-5d28-4c72-9158-dfb4282c504f\",\n      \"target\": \"5c11ed5f-c993-4940-89d0-08d186e903f9\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ],\n  \"outputs\": []\n}\n\ndef _curio_node():\n\n\n    input_data = pool_c528f5bc_5d28_4c72_9158_dfb4282c504f\n\n    spec = {\n      \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.json\",\n      \"description\": \"Dot Density Map of Green Roof Locations in Chicago with Zoom & Pan\",\n      \"width\": 500,\n      \"height\": 600,\n      \"title\": \"Green Roof Locations in Chicago\",\n      \"mark\": \"circle\",\n      \"selection\": {\n        \"grid\": {\n          \"type\": \"interval\",\n          \"bind\": \"scales\"\n        }\n      },\n      \"encoding\": {\n        \"x\": {\n          \"field\": \"LONGITUDE\",\n          \"type\": \"quantitative\",\n          \"scale\": { \"domain\": [-88.0, -87.5] },\n          \"axis\": { \"title\": \"Longitude\" }\n        },\n        \"y\": {\n          \"field\": \"LATITUDE\",\n          \"type\": \"quantitative\",\n          \"scale\": { \"domain\": [41.6, 42.1] },\n          \"axis\": { \"title\": \"Latitude\" }\n        },\n        \"size\": {\n          \"field\": \"VEGETATED_SQFT\",\n          \"type\": \"quantitative\",\n          \"legend\": { \"title\": \"Vegetated Sqft\" }\n        },\n        \"tooltip\": [\n          { \"field\": \"VEGETATED_SQFT\", \"type\": \"quantitative\" },\n          { \"field\": \"TOTAL_ROOF_SQFT\", \"type\": \"quantitative\" },\n          { \"field\": \"zip\", \"type\": \"nominal\" }\n        ]\n      },\n      \"config\": {\n        \"view\": { \"stroke\": \"transparent\" }\n      }\n    }\n\n    values = input_data\n    if hasattr(input_data, \"to_dict\"):\n        values = input_data.to_dict(orient=\"records\")\n\n    if isinstance(spec, dict):\n        spec[\"data\"] = {\"values\": values}\n\n    from IPython.display import display\n    display({\"application/vnd.vegalite.v5+json\": spec, \"text/plain\": spec}, raw=True)\n\n    return input_data\n\n\n_curio_output = _curio_node()\n\ntry:\n    result_5c11ed5f_c993_4940_89d0_08d186e903f9 = _curio_output\nexcept NameError:\n    result_5c11ed5f_c993_4940_89d0_08d186e903f9 = None\n",
+      "metadata": {
+        "id": "5c11ed5f-c993-4940-89d0-08d186e903f9",
+        "language": "python"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": "__trill_node__ = {\n    \"id\": \"a9995883-f2ea-4b42-b74d-59ebc727afc6\",\n    \"type\": \"DATA_TRANSFORMATION\",\n    \"in\": \"DEFAULT\",\n    \"out\": \"DEFAULT\"\n}\n\n__trill_connections__ = {\n  \"inputs\": [\n    {\n      \"source\": \"c528f5bc-5d28-4c72-9158-dfb4282c504f\",\n      \"target\": \"a9995883-f2ea-4b42-b74d-59ebc727afc6\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ],\n  \"outputs\": [\n    {\n      \"source\": \"a9995883-f2ea-4b42-b74d-59ebc727afc6\",\n      \"target\": \"d23e2587-57bf-4db4-84fe-cdb7c2de638d\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ]\n}\n\ndef _curio_node():\n\n    input_0 = pool_c528f5bc_5d28_4c72_9158_dfb4282c504f\n    arg = input_0\n\n    import geopandas as gpd\n\n    joined = arg\n\n    # filter out the top 10 zip codes from the joined dataframe on 'zip' by square feet\n    top_10_largest = joined.groupby('zip')['VEGETATED_SQFT'].sum().reset_index().sort_values(by='VEGETATED_SQFT', ascending=False).head(10)\n\n    return top_10_largest\n\n\n_curio_output = _curio_node()\n\ntry:\n    result_a9995883_f2ea_4b42_b74d_59ebc727afc6 = _curio_output\nexcept NameError:\n    result_a9995883_f2ea_4b42_b74d_59ebc727afc6 = None\n",
+      "metadata": {
+        "id": "a9995883-f2ea-4b42-b74d-59ebc727afc6",
+        "language": "python"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": "__trill_node__ = {\n    \"id\": \"d23e2587-57bf-4db4-84fe-cdb7c2de638d\",\n    \"type\": \"VIS_VEGA\",\n    \"in\": \"DEFAULT\",\n    \"out\": \"DEFAULT\"\n}\n\n__trill_connections__ = {\n  \"inputs\": [\n    {\n      \"source\": \"a9995883-f2ea-4b42-b74d-59ebc727afc6\",\n      \"target\": \"d23e2587-57bf-4db4-84fe-cdb7c2de638d\",\n      \"sourceHandle\": \"out\",\n      \"targetHandle\": \"in\"\n    }\n  ],\n  \"outputs\": []\n}\n\ndef _curio_node():\n\n\n    input_data = result_a9995883_f2ea_4b42_b74d_59ebc727afc6\n\n    spec = {\n      \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.json\",\n      \"description\": \"Top 10 largest zip codes by green roof area\",\n      \"width\": 400,\n      \"height\": 200,\n      \"selection\": {\n        \"zip_select\": {\n          \"type\": \"multi\",\n          \"fields\": [\"zip\"],\n          \"toggle\": \"event.shiftKey\"\n        }\n      },\n      \"mark\": { \"type\": \"bar\", \"stroke\": \"black\", \"color\": \"green\" },\n      \"encoding\": {\n        \"x\": {\n          \"field\": \"VEGETATED_SQFT\",\n          \"type\": \"quantitative\",\n          \"axis\": {\n            \"title\": \"Total Vegetated Roof Size (sqft)\",\n            \"values\": [100000, 250000, 500000, 1000000],\n            \"format\": \",d\"\n          }\n        },\n        \"y\": {\n          \"field\": \"zip\",\n          \"type\": \"nominal\",\n          \"sort\": \"-x\",\n          \"axis\": { \"title\": \"Zip Code\" }\n        },\n        \"color\": {\n          \"field\": \"zip\",\n          \"type\": \"nominal\",\n          \"scale\": { \"scheme\": \"category20\" }\n        },\n        \"opacity\": {\n          \"condition\": { \"selection\": \"zip_select\", \"value\": 1 },\n          \"value\": 0.3\n        },\n        \"tooltip\": [\n          { \"field\": \"zip\", \"type\": \"nominal\" },\n          { \"field\": \"VEGETATED_SQFT\", \"type\": \"quantitative\" }\n        ]\n      }\n    }\n\n    values = input_data\n    if hasattr(input_data, \"to_dict\"):\n        values = input_data.to_dict(orient=\"records\")\n\n    if isinstance(spec, dict):\n        spec[\"data\"] = {\"values\": values}\n\n    from IPython.display import display\n    display({\"application/vnd.vegalite.v5+json\": spec, \"text/plain\": spec}, raw=True)\n\n    return input_data\n\n\n_curio_output = _curio_node()\n\ntry:\n    result_d23e2587_57bf_4db4_84fe_cdb7c2de638d = _curio_output\nexcept NameError:\n    result_d23e2587_57bf_4db4_84fe_cdb7c2de638d = None\n",
+      "metadata": {
+        "id": "d23e2587-57bf-4db4-84fe-cdb7c2de638d",
+        "language": "python"
+      }
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 4
+}