{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Google Suggestions\n",
"\n",
"This is a demo with tooltips. It provides a set of Google queries starting with \"What if %countryname% ...\". The result will be shown on the map when you hover over the country.\n",
"\n",
"To try queries starting with other words change the START_OF_QUERY constant. In this case, you need to specify the path to your chromedriver (PATH_TO_CHROMEDRIVER), which is used to get data. It can be downloaded [here](https://chromedriver.chromium.org/downloads)."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:39:53.286565Z",
"iopub.status.busy": "2024-04-17T07:39:53.286476Z",
"iopub.status.idle": "2024-04-17T07:39:53.652745Z",
"shell.execute_reply": "2024-04-17T07:39:53.652513Z"
}
},
"outputs": [],
"source": [
"import os\n",
"\n",
"import pandas as pd\n",
"import geopandas as gpd\n",
"from selenium import webdriver\n",
"from selenium.webdriver.common.by import By\n",
"from selenium.webdriver.support.ui import WebDriverWait\n",
"from selenium.webdriver.support import expected_conditions as EC\n",
"from selenium.common.exceptions import WebDriverException\n",
"\n",
"from lets_plot import *"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:39:53.654276Z",
"iopub.status.busy": "2024-04-17T07:39:53.654145Z",
"iopub.status.idle": "2024-04-17T07:39:53.656453Z",
"shell.execute_reply": "2024-04-17T07:39:53.656280Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"LetsPlot.setup_html()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:39:53.669520Z",
"iopub.status.busy": "2024-04-17T07:39:53.669348Z",
"iopub.status.idle": "2024-04-17T07:39:53.670794Z",
"shell.execute_reply": "2024-04-17T07:39:53.670611Z"
}
},
"outputs": [],
"source": [
"START_OF_QUERY = 'What if'\n",
"SUGGESTION_STUB = 'no data'\n",
"PATH_TO_CHROMEDRIVER = ''\n",
"PATH_TO_DATA = \"https://raw.githubusercontent.com/JetBrains/lets-plot-docs/master/data/google_suggestions_2020.csv\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:39:53.671856Z",
"iopub.status.busy": "2024-04-17T07:39:53.671740Z",
"iopub.status.idle": "2024-04-17T07:39:53.673834Z",
"shell.execute_reply": "2024-04-17T07:39:53.673652Z"
}
},
"outputs": [],
"source": [
"def get_naturalearth_data(data_type=\"admin_0_countries\", columns=[\"NAME\", \"geometry\"]):\n",
" import shapefile\n",
" from shapely.geometry import shape\n",
"\n",
" naturalearth_url = \"https://raw.githubusercontent.com/JetBrains/lets-plot-docs/master/\" + \\\n",
" \"data/naturalearth/{0}/data.shp?raw=true\".format(data_type)\n",
" sf = shapefile.Reader(naturalearth_url)\n",
"\n",
" gdf = gpd.GeoDataFrame(\n",
" [\n",
" dict(zip([field[0] for field in sf.fields[1:]], record))\n",
" for record in sf.records()\n",
" ],\n",
" geometry=[shape(s) for s in sf.shapes()]\n",
" )[columns]\n",
" gdf.columns = [col.lower() for col in gdf.columns]\n",
"\n",
" return gdf"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:39:53.674925Z",
"iopub.status.busy": "2024-04-17T07:39:53.674809Z",
"iopub.status.idle": "2024-04-17T07:39:53.676542Z",
"shell.execute_reply": "2024-04-17T07:39:53.676345Z"
}
},
"outputs": [],
"source": [
"def split_list_to_bunches(l, *, bunch_size=1):\n",
" if bunch_size < 1:\n",
" raise Exception('Wrong input')\n",
" bunches = []\n",
" i = 0\n",
" while i < len(l):\n",
" bunches.append([])\n",
" for j in range(bunch_size):\n",
" if i == len(l):\n",
" break\n",
" bunches[-1].append(l[i])\n",
" i += 1\n",
" return bunches"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:39:53.677592Z",
"iopub.status.busy": "2024-04-17T07:39:53.677477Z",
"iopub.status.idle": "2024-04-17T07:39:53.680103Z",
"shell.execute_reply": "2024-04-17T07:39:53.679929Z"
}
},
"outputs": [],
"source": [
"def get_suggestions_data(countries, *, start_of_query='', driver_path='', data_path=''):\n",
" BUNCH_SIZE = 20\n",
" if not os.path.isfile(driver_path):\n",
" return pd.read_csv(data_path)\n",
" suggestions = []\n",
" for countries_bunch in split_list_to_bunches(countries, bunch_size=BUNCH_SIZE):\n",
" with webdriver.Chrome(executable_path=driver_path) as driver:\n",
" driver.get('http://www.google.com')\n",
" for country in countries_bunch:\n",
" query = '{0} {1} '.format(start_of_query, country).lower()\n",
" suggestion = SUGGESTION_STUB\n",
" try:\n",
" input_elem = WebDriverWait(driver, 2).until(\n",
" EC.presence_of_element_located((By.CSS_SELECTOR, 'input[role=\"combobox\"]'))\n",
" )\n",
" input_elem.send_keys(query)\n",
" li_elem = WebDriverWait(driver, 1).until(\n",
" EC.presence_of_element_located((By.CSS_SELECTOR, 'ul[role=\"listbox\"]>li'))\n",
" )\n",
" text_container_elems = driver.find_elements_by_css_selector('ul[role=\"listbox\"] div[role=\"option\"]')\n",
" suggestion = next(\n",
" elem.get_attribute('textContent') for elem in text_container_elems\n",
" if elem.get_attribute('textContent').find(start_of_query.lower()) == 0\n",
" )\n",
" except WebDriverException:\n",
" pass\n",
" except StopIteration:\n",
" pass\n",
" suggestions.append(suggestion)\n",
" driver.refresh()\n",
" return pd.DataFrame(dict(country=countries, suggestion=suggestions))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:39:53.681417Z",
"iopub.status.busy": "2024-04-17T07:39:53.681127Z",
"iopub.status.idle": "2024-04-17T07:39:54.732118Z",
"shell.execute_reply": "2024-04-17T07:39:54.731888Z"
}
},
"outputs": [],
"source": [
"world_gdf = get_naturalearth_data(columns=[\"NAME\", \"ISO_A3\", \"CONTINENT\", \"POP_EST\", \"GDP_MD\", \"geometry\"])\n",
"\n",
"suggestions_df = get_suggestions_data(world_gdf['name'], \\\n",
" start_of_query=START_OF_QUERY, \\\n",
" driver_path=PATH_TO_CHROMEDRIVER, \\\n",
" data_path=PATH_TO_DATA)\n",
"\n",
"df = suggestions_df.merge(world_gdf, left_on='country', right_on='name')\n",
"gdf = gpd.GeoDataFrame(df, geometry='geometry')\n",
"\n",
"suggestions_gdf = gdf[~(gdf.suggestion == SUGGESTION_STUB)]\n",
"no_data_gdf = gdf[gdf.suggestion == SUGGESTION_STUB]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:39:54.733597Z",
"iopub.status.busy": "2024-04-17T07:39:54.733503Z",
"iopub.status.idle": "2024-04-17T07:39:54.788761Z",
"shell.execute_reply": "2024-04-17T07:39:54.788559Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ggplot() + \\\n",
" geom_map(data=no_data_gdf, fill='gray', size=.2, alpha=.5,\n",
" tooltips=layer_tooltips().line('@name')) + \\\n",
" geom_map(aes(fill='suggestion'), data=suggestions_gdf, size=.2, alpha=.5,\n",
" tooltips=layer_tooltips().line('@name').line('Google suggestion|@suggestion')) + \\\n",
" scale_fill_discrete(name='Google suggestion') + \\\n",
" ggtitle('First Google Query Suggestion Starting with \\'%s \\'' % START_OF_QUERY) + \\\n",
" ggsize(700, 500) + \\\n",
" theme_void() + theme(legend_position='none')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Gray means there were no suggestions for that query."
]
}
],
"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": "3.10.13"
}
},
"nbformat": 4,
"nbformat_minor": 4
}