Add visualization

.ipynb_checkpoints/facets-dive-checkpoint.ipynb

@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d5d0ea64",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>.container { width:95% !important; }</style>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from IPython.core.display import display, HTML, Image\n",
+    "display(HTML(\"<style>.container { width:95% !important; }</style>\"))\n",
+    "%config IPCompleter.use_jedi=False"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "403c4b8a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from IPython.display import Markdown, display, HTML, IFrame\n",
+    "from facets_overview.generic_feature_statistics_generator import GenericFeatureStatisticsGenerator\n",
+    "import base64"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "1c48706a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('./adult.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c000f04d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Private             22696\n",
+       "Self-emp-not-inc     2541\n",
+       "Local-gov            2093\n",
+       "?                    1836\n",
+       "State-gov            1298\n",
+       "Self-emp-inc         1116\n",
+       "Federal-gov           960\n",
+       "Without-pay            14\n",
+       "Never-worked            7\n",
+       "Name: workclass, dtype: int64"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['workclass'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "85b71af5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sprite_size = 32 if len(df.index)>50000 else 64\n",
+    "\n",
+    "jsonstr = df.to_json(orient='records') \n",
+    "HTML_TEMPLATE = \"\"\"\n",
+    "        <script src=\"https://cdnjs.cloudflare.com/ajax/libs/webcomponentsjs/1.3.3/webcomponents-lite.js\"></script>\n",
+    "        <link rel=\"import\" href=\"https://raw.githubusercontent.com/PAIR-code/facets/1.0.0/facets-dist/facets-jupyter.html\">\n",
+    "        <facets-dive sprite-image-width=\"{sprite_size}\" sprite-image-height=\"{sprite_size}\" id=\"elem\" height=\"1200\"></facets-dive>\n",
+    "        <script>\n",
+    "          document.querySelector(\"#elem\").data = {jsonstr};\n",
+    "        </script>\"\"\"\n",
+    "html = HTML_TEMPLATE.format(jsonstr=jsonstr, sprite_size=sprite_size)\n",
+    "with open(\"index.html\",'w') as fo:\n",
+    "    fo.write(html)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fce8e9f4",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Dockerfile

@@ -0,0 +1,3 @@
+FROM jupyter/base-notebook:latest
+
+RUN pip install --use-feature=2020-resolver pandas facets-overview

Makefile

@@ -0,0 +1,13 @@
+VERSION := 0.0.1
+NAME := facets-dive
+REPO := cakiki
+
+build:
+	docker build -f Dockerfile -t ${REPO}/${NAME}:${VERSION} -t ${REPO}/${NAME}:latest .
+
+run: build
+	docker run --rm -it -p 8888:8888 --mount type=bind,source=${PWD},target=/home/jovyan/work --name ${NAME} --workdir=/home/jovyan/work ${REPO}/${NAME}:${VERSION} && make -s clean
+
+push: build
+	docker push ${REPO}/${NAME}:${VERSION} && docker push ${REPO}/${NAME}:latest
+

facets-dive.ipynb

@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d5d0ea64",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>.container { width:95% !important; }</style>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from IPython.core.display import display, HTML, Image\n",
+    "display(HTML(\"<style>.container { width:95% !important; }</style>\"))\n",
+    "%config IPCompleter.use_jedi=False"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "403c4b8a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from IPython.display import Markdown, display, HTML, IFrame\n",
+    "from facets_overview.generic_feature_statistics_generator import GenericFeatureStatisticsGenerator\n",
+    "import base64"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "1c48706a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('./adult.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c000f04d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Private             22696\n",
+       "Self-emp-not-inc     2541\n",
+       "Local-gov            2093\n",
+       "?                    1836\n",
+       "State-gov            1298\n",
+       "Self-emp-inc         1116\n",
+       "Federal-gov           960\n",
+       "Without-pay            14\n",
+       "Never-worked            7\n",
+       "Name: workclass, dtype: int64"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['workclass'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "85b71af5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sprite_size = 32 if len(df.index)>50000 else 64\n",
+    "\n",
+    "jsonstr = df.to_json(orient='records') \n",
+    "HTML_TEMPLATE = \"\"\"\n",
+    "        <script src=\"https://cdnjs.cloudflare.com/ajax/libs/webcomponentsjs/1.3.3/webcomponents-lite.js\"></script>\n",
+    "        <link rel=\"import\" href=\"https://raw.githubusercontent.com/PAIR-code/facets/1.0.0/facets-dist/facets-jupyter.html\">\n",
+    "        <facets-dive sprite-image-width=\"{sprite_size}\" sprite-image-height=\"{sprite_size}\" id=\"elem\" height=\"1200\"></facets-dive>\n",
+    "        <script>\n",
+    "          document.querySelector(\"#elem\").data = {jsonstr};\n",
+    "        </script>\"\"\"\n",
+    "html = HTML_TEMPLATE.format(jsonstr=jsonstr, sprite_size=sprite_size)\n",
+    "with open(\"index.html\",'w') as fo:\n",
+    "    fo.write(html)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fce8e9f4",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}