{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Test notebook Meteorites"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import requests\n",
    "from IPython.display import display\n",
    "from IPython.utils.capture import capture_output\n",
    "\n",
    "import ydata_profiling\n",
    "from ydata_profiling.utils.cache import cache_file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "file_name = cache_file(\n",
    "    \"meteorites.csv\",\n",
    "    \"https://data.nasa.gov/api/views/gh4g-9sfh/rows.csv?accessType=DOWNLOAD\",\n",
    ")\n",
    "\n",
    "df = pd.read_csv(file_name)\n",
    "\n",
    "# Note: Pandas does not support dates before 1880, so we ignore these for this analysis\n",
    "df[\"year\"] = pd.to_datetime(df[\"year\"], errors=\"coerce\")\n",
    "\n",
    "# Example: Constant variable\n",
    "df[\"source\"] = \"NASA\"\n",
    "\n",
    "# Example: Boolean variable\n",
    "df[\"boolean\"] = np.random.choice([True, False], df.shape[0])\n",
    "\n",
    "# Example: Mixed with base types\n",
    "df[\"mixed\"] = np.random.choice([1, \"A\"], df.shape[0])\n",
    "\n",
    "# Example: Highly correlated variables\n",
    "df[\"reclat_city\"] = df[\"reclat\"] + np.random.normal(scale=5, size=(len(df)))\n",
    "\n",
    "# Example: Duplicate observations\n",
    "duplicates_to_add = pd.DataFrame(df.iloc[0:10])\n",
    "duplicates_to_add[\"name\"] = duplicates_to_add[\"name\"] + \" copy\"\n",
    "\n",
    "df = pd.concat([df, duplicates_to_add], ignore_index=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Inline report without saving\n",
    "with capture_output() as out:\n",
    "    pr = df.profile_report(\n",
    "        sort=None,\n",
    "        html={\"style\": {\"full_width\": True}},\n",
    "        progress_bar=False,\n",
    "        minimal=True,\n",
    "    )\n",
    "    display(pr)\n",
    "\n",
    "assert len(out.outputs) == 2\n",
    "assert out.outputs[0].data[\"text/plain\"] == \"<IPython.core.display.HTML object>\"\n",
    "assert out.outputs[1].data[\"text/plain\"] == \"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# There should also 2 progress bars in minimal mode\n",
    "with capture_output() as out:\n",
    "    pfr = df.profile_report(\n",
    "        html={\"style\": {\"full_width\": True}},\n",
    "        minimal=True,\n",
    "        progress_bar=True,\n",
    "        lazy=False,\n",
    "    )\n",
    "\n",
    "assert all(\n",
    "    any(v in s.data[\"text/plain\"] for v in [\"%|\", \"FloatProgress\"]) for s in out.outputs\n",
    ")\n",
    "assert len(out.outputs) == 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Write to a file\n",
    "with capture_output() as out:\n",
    "    pfr.to_file(\"/tmp/example.html\")\n",
    "\n",
    "assert all(\n",
    "    any(v in s.data[\"text/plain\"] for v in [\"%|\", \"FloatProgress\"]) for s in out.outputs\n",
    ")\n",
    "assert len(out.outputs) == 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Print existing ProfileReport object inline\n",
    "with capture_output() as out:\n",
    "    display(pfr)\n",
    "\n",
    "assert len(out.outputs) == 2\n",
    "assert out.outputs[0].data[\"text/plain\"] == \"<IPython.core.display.HTML object>\"\n",
    "assert out.outputs[1].data[\"text/plain\"] == \"\""
   ]
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}