{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Stock exchange – visualising page data"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import altair as alt\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"complete_page_list.csv\", parse_dates=[\"date\"])"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"A 27244\n",
"M 24538\n",
"N 20971\n",
"U 1\n",
"Name: session, dtype: int64"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[\"session\"].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"df[\"year\"] = df[\"date\"].dt.year"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"df_years = df[\"year\"].value_counts().to_frame().reset_index()\n",
"df_years.columns = [\"year\", \"count\"]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
""
],
"text/plain": [
"alt.Chart(...)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Pages per year\n",
"\n",
"alt.Chart(df_years).mark_bar().encode(x=\"year:N\", y=\"count:Q\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"df_dates = pd.DataFrame(df[\"date\"].unique())\n",
"df_dates[\"year\"] = df_dates[0].dt.year\n",
"df_years_dates = df_dates[\"year\"].value_counts().to_frame().reset_index()\n",
"df_years_dates.columns = [\"year\", \"count\"]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
""
],
"text/plain": [
"alt.Chart(...)"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Days per year\n",
"\n",
"alt.Chart(df_years_dates).mark_bar().encode(x=\"year:N\", y=\"count:Q\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"orders = {\"M\": 1, \"N\": 2, \"A\": 3, \"U\": 4}\n",
"df_sessions = (\n",
" df.groupby(by=\"year\")[\"session\"]\n",
" .value_counts()\n",
" .to_frame()\n",
" .rename(columns={\"session\": \"count\"}, level=0)\n",
" .reset_index()\n",
")\n",
"df_sessions[\"order\"] = df_sessions[\"session\"].apply(lambda x: orders[x])"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
""
],
"text/plain": [
"alt.Chart(...)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Days per year\n",
"\n",
"alt.Chart(df_sessions).mark_bar().encode(\n",
" x=\"year:N\",\n",
" y=\"count:Q\",\n",
" color=\"session:N\",\n",
" order=alt.Order(\n",
" # Sort the segments of the bars by this field\n",
" \"order\",\n",
" sort=\"ascending\",\n",
" ),\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"Created by [Tim Sherratt](https://timsherratt.org) for the [GLAM Workbench](https://glam-workbench.github.io/)."
]
}
],
"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": "3.8.12"
}
},
"nbformat": 4,
"nbformat_minor": 4
}