{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Time Series Visualizations\n",
"\n",
"This notebook demonstrates how to use Lets-Plot to investigate time series.\n",
"\n",
"The data is provided by [Kaggle](https://www.kaggle.com/sumanthvrao/daily-climate-time-series-data)."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:12.579573Z",
"iopub.status.busy": "2024-03-26T14:41:12.579494Z",
"iopub.status.idle": "2024-03-26T14:41:12.902600Z",
"shell.execute_reply": "2024-03-26T14:41:12.902131Z"
}
},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"from lets_plot import *\n",
"from lets_plot.mapping import as_discrete"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:12.904155Z",
"iopub.status.busy": "2024-03-26T14:41:12.904024Z",
"iopub.status.idle": "2024-03-26T14:41:12.906430Z",
"shell.execute_reply": "2024-03-26T14:41:12.906241Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"LetsPlot.setup_html()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Preparation"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:12.919658Z",
"iopub.status.busy": "2024-03-26T14:41:12.919548Z",
"iopub.status.idle": "2024-03-26T14:41:13.319405Z",
"shell.execute_reply": "2024-03-26T14:41:13.319183Z"
}
},
"outputs": [],
"source": [
"df = pd.read_csv(\"https://raw.githubusercontent.com/JetBrains/lets-plot-docs/master/data/delhi_climate.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.320633Z",
"iopub.status.busy": "2024-03-26T14:41:13.320515Z",
"iopub.status.idle": "2024-03-26T14:41:13.325017Z",
"shell.execute_reply": "2024-03-26T14:41:13.324813Z"
}
},
"outputs": [],
"source": [
"df = df.rename(columns={\"meantemp\": \"mean temperature\", \"wind_speed\": \"wind speed\"})\n",
"df.date = pd.to_datetime(df.date)\n",
"df[\"day\"] = df.date.dt.day\n",
"df[\"month\"] = df.date.dt.month\n",
"df[\"year\"] = df.date.dt.year\n",
"df = df[df.year < 2017]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### General Information"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.326320Z",
"iopub.status.busy": "2024-03-26T14:41:13.326154Z",
"iopub.status.idle": "2024-03-26T14:41:13.372372Z",
"shell.execute_reply": "2024-03-26T14:41:13.372135Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ggplot(df, aes(\"date\", \"mean temperature\")) + \\\n",
" geom_line(aes(group=\"year\", color=as_discrete(\"year\")), size=1) + \\\n",
" scale_x_datetime(breaks=df[df.date.dt.day == 1].date, format=\"%b %Y\") + \\\n",
" facet_grid(x=\"year\", scales='free') + \\\n",
" ggtitle(\"Mean Temperature Along Period Under Review\") + \\\n",
" ggsize(1000, 500) + \\\n",
" theme(legend_position='bottom')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.373637Z",
"iopub.status.busy": "2024-03-26T14:41:13.373529Z",
"iopub.status.idle": "2024-03-26T14:41:13.439784Z",
"shell.execute_reply": "2024-03-26T14:41:13.439560Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"p1 = ggplot() + \\\n",
" geom_boxplot(aes(x=\"year\", y=\"mean temperature\", \\\n",
" fill=as_discrete(\"year\")), \\\n",
" data=df, size=2, alpha=.5) + \\\n",
" scale_x_discrete(name=\"year\") + \\\n",
" ggtitle(\"Mean Temperature Aggregated\") + \\\n",
" theme(legend_position='bottom', panel_grid='blank')\n",
"p2 = ggplot() + \\\n",
" geom_boxplot(aes(x=\"month\", y=\"mean temperature\", \\\n",
" fill=as_discrete(\"year\")), \\\n",
" data=df, size=.75, alpha=.5) + \\\n",
" scale_x_continuous(breaks=list(range(1, 13))) + \\\n",
" facet_grid(x=\"year\") + \\\n",
" ggtitle(\"Mean Temperature by Month\") + \\\n",
" theme(legend_position='none', panel_grid='blank')\n",
"\n",
"w, h = 1000, 300\n",
"bunch = GGBunch()\n",
"bunch.add_plot(p1, 0, 0, w, h)\n",
"bunch.add_plot(p2, 0, h, w, h)\n",
"bunch.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Year-to-Year Temperature Comparison"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.441177Z",
"iopub.status.busy": "2024-03-26T14:41:13.441061Z",
"iopub.status.idle": "2024-03-26T14:41:13.457533Z",
"shell.execute_reply": "2024-03-26T14:41:13.457245Z"
},
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ggplot(df, aes(\"day\", \"mean temperature\")) + \\\n",
" geom_line(aes(group=\"year\", color=as_discrete(\"year\")), size=2, \\\n",
" tooltips=layer_tooltips().title(\"@year\")\\\n",
" .format(\"@{mean temperature}\", \".2f\")\\\n",
" .line(\"@|@{mean temperature}\")\\\n",
" .line(\"date|@month/@day/@year\")) + \\\n",
" scale_x_continuous(breaks=list(range(1, 32))) + \\\n",
" facet_grid(y=\"month\", scales='free') + \\\n",
" ylab(\"month\") + \\\n",
" ggtitle(\"Mean Temperature for Each Month\") + \\\n",
" theme(legend_position='bottom')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Most Common Temperature Values"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.458786Z",
"iopub.status.busy": "2024-03-26T14:41:13.458622Z",
"iopub.status.idle": "2024-03-26T14:41:13.476371Z",
"shell.execute_reply": "2024-03-26T14:41:13.476143Z"
},
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ggplot(df, aes(x=\"mean temperature\")) + \\\n",
" geom_histogram(aes(group=\"year\", fill=as_discrete(\"year\")), \\\n",
" color='black', bins=15, size=.5, alpha=.5, \\\n",
" tooltips=layer_tooltips().line(\"count|@..count..\")\\\n",
" .format(\"@{mean temperature}\", \".2f\")\\\n",
" .line(\"@|@{mean temperature}\")\\\n",
" .line(\"@|@month\")\\\n",
" .line(\"@|@year\")) + \\\n",
" facet_grid(x=\"month\", y=\"year\") + \\\n",
" xlab(\"month\") + ylab(\"year\") + \\\n",
" ggtitle(\"Most Common Temperature\") + \\\n",
" ggsize(1000, 500) + \\\n",
" theme_classic() + theme(legend_position='bottom')"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.477539Z",
"iopub.status.busy": "2024-03-26T14:41:13.477410Z",
"iopub.status.idle": "2024-03-26T14:41:13.487119Z",
"shell.execute_reply": "2024-03-26T14:41:13.486920Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"int_mean_temp_df = df[[\"mean temperature\", \"month\", \"year\"]].copy()\n",
"int_mean_temp_df[\"mean temperature\"] = int_mean_temp_df[\"mean temperature\"].astype(int)\n",
"\n",
"ggplot(int_mean_temp_df, aes(\"month\", \"mean temperature\", fill=\"mean temperature\")) + \\\n",
" geom_bin2d(stat='identity', size=.5, color='white', alpha=.2,\n",
" tooltips=layer_tooltips().format(\"@{mean temperature}\", \".2f\")\\\n",
" .line(\"@|@{mean temperature}\")\\\n",
" .format(\"@month\", \"d\")\n",
" .line(\"@|@month\")\\\n",
" .title(\"@year\")) + \\\n",
" scale_x_continuous(breaks=list(range(1, 13))) + \\\n",
" scale_fill_gradient(low='#abd9e9', high='#d7191c') + \\\n",
" facet_grid(x=\"year\") + \\\n",
" coord_fixed(ratio=.5) + \\\n",
" xlab(\"\") + \\\n",
" ggtitle(\"Heatmap of Temperatures by Year\") + \\\n",
" ggsize(1000, 500) + \\\n",
" theme_classic() + theme(legend_position='bottom')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Observing Mean Temperature and Wind Speed Correlation"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.488379Z",
"iopub.status.busy": "2024-03-26T14:41:13.488205Z",
"iopub.status.idle": "2024-03-26T14:41:13.502686Z",
"shell.execute_reply": "2024-03-26T14:41:13.502474Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ggplot(df, aes(\"wind speed\", y=\"mean temperature\")) + \\\n",
" geom_point(aes(color=\"mean temperature\", fill=\"mean temperature\"), \\\n",
" shape=21, size=3, alpha=.2) + \\\n",
" scale_color_gradient(low='#abd9e9', high='#d7191c') + \\\n",
" scale_fill_gradient(low='#abd9e9', high='#d7191c') + \\\n",
" facet_grid(x=\"year\") + \\\n",
" ggtitle(\"Relation Between Mean Temperature and Wind Speed\") + \\\n",
" ggsize(1000, 500) + \\\n",
" theme_classic()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Observing Mean Temperature and Humidity Correlation"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.503935Z",
"iopub.status.busy": "2024-03-26T14:41:13.503759Z",
"iopub.status.idle": "2024-03-26T14:41:13.518321Z",
"shell.execute_reply": "2024-03-26T14:41:13.518117Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ggplot(df, aes(\"humidity\", \"mean temperature\")) + \\\n",
" geom_point(aes(color=\"humidity\", fill=\"humidity\"), \\\n",
" shape=21, size=3, alpha=.2) + \\\n",
" scale_color_gradient(low='#fdae61', high='#2c7bb6') + \\\n",
" scale_fill_gradient(low='#fdae61', high='#2c7bb6') + \\\n",
" facet_grid(x=\"year\") + \\\n",
" ggtitle(\"Relation Between Mean Temperature and Humidity\") + \\\n",
" ggsize(1000, 500) + \\\n",
" theme_classic()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### In Search of Correlation on Lag Scatter Plots"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.519621Z",
"iopub.status.busy": "2024-03-26T14:41:13.519440Z",
"iopub.status.idle": "2024-03-26T14:41:13.544105Z",
"shell.execute_reply": "2024-03-26T14:41:13.543862Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"df_shifted_by_day = df[[\"mean temperature\", \"year\"]].copy()\n",
"df_shifted_by_day[\"shifted mean temperature\"] = df[\"mean temperature\"].shift(-1)\n",
"df_shifted_by_day = df_shifted_by_day.dropna()\n",
"\n",
"p1 = ggplot(df_shifted_by_day, aes(\"mean temperature\", \"shifted mean temperature\")) + \\\n",
" geom_point(aes(color=\"mean temperature\", fill=\"mean temperature\"), \\\n",
" shape=21, size=3, alpha=.2) + \\\n",
" scale_color_gradient(low='#abd9e9', high='#d7191c') + \\\n",
" scale_fill_gradient(low='#abd9e9', high='#d7191c') + \\\n",
" facet_grid(x=\"year\") + \\\n",
" coord_fixed(ratio=1) + \\\n",
" ggtitle(\"One Day Lag Scatter Plot\") + \\\n",
" theme_classic()\n",
"\n",
"df_shifted_by_month = df[[\"mean temperature\", \"year\"]].copy()\n",
"df_shifted_by_month[\"shifted mean temperature\"] = df[\"mean temperature\"].shift(-30)\n",
"df_shifted_by_month = df_shifted_by_month.dropna()\n",
"\n",
"p2 = ggplot(df_shifted_by_month, aes(\"mean temperature\", \"shifted mean temperature\")) + \\\n",
" geom_point(aes(color=\"mean temperature\", fill=\"mean temperature\"), \\\n",
" shape=21, size=3, alpha=.2) + \\\n",
" scale_color_gradient(low='#abd9e9', high='#d7191c') + \\\n",
" scale_fill_gradient(low='#abd9e9', high='#d7191c') + \\\n",
" facet_grid(x=\"year\") + \\\n",
" coord_fixed(ratio=1) + \\\n",
" ggtitle(\"One Month Lag Scatter Plot\") + \\\n",
" theme_classic()\n",
"\n",
"df_shifted_by_year = df[[\"mean temperature\", \"year\"]].copy()\n",
"df_shifted_by_year[\"shifted mean temperature\"] = df[\"mean temperature\"].shift(-365)\n",
"df_shifted_by_year = df_shifted_by_year.dropna()[:-1]\n",
"\n",
"p3 = ggplot(df_shifted_by_year, aes(\"mean temperature\", \"shifted mean temperature\")) + \\\n",
" geom_point(aes(color=\"mean temperature\", fill=\"mean temperature\"), \\\n",
" shape=21, size=3, alpha=.2) + \\\n",
" scale_color_gradient(low='#abd9e9', high='#d7191c') + \\\n",
" scale_fill_gradient(low='#abd9e9', high='#d7191c') + \\\n",
" facet_grid(x=\"year\") + \\\n",
" coord_fixed(ratio=1) + \\\n",
" ggtitle(\"One Year Lag Scatter Plot\") + \\\n",
" theme_classic()\n",
"\n",
"w, h = 1000, 300\n",
"bunch = GGBunch()\n",
"bunch.add_plot(p1, 0, 0, w, h)\n",
"bunch.add_plot(p2, 0, h, w, h)\n",
"bunch.add_plot(p3, 0, 2 * h, w, h)\n",
"bunch.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Annual Path of Mean Temperature and Humidity"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.545401Z",
"iopub.status.busy": "2024-03-26T14:41:13.545221Z",
"iopub.status.idle": "2024-03-26T14:41:13.551192Z",
"shell.execute_reply": "2024-03-26T14:41:13.551003Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"mean_df = df.groupby(by=[\"year\", \"month\"]).mean(numeric_only=True)[[\"mean temperature\", \"humidity\"]].reset_index()\n",
"\n",
"ggplot(mean_df, aes(\"humidity\", \"mean temperature\")) + \\\n",
" geom_path(color='#99d8c9', size=1) + \\\n",
" geom_point(aes(fill=\"month\"), shape=21, size=3, color='#00441b',\n",
" tooltips=layer_tooltips().title(\"@year\")\\\n",
" .line(\"month|@month\")\\\n",
" .format(\"@humidity\", \".2f\")\\\n",
" .line(\"@|@humidity\")\\\n",
" .format(\"@{mean temperature}\", \".2f\")\\\n",
" .line(\"mean temperature|@{mean temperature}\")) + \\\n",
" scale_fill_gradient(name=\"\", low='#e5f5f9', high='#2ca25f') + \\\n",
" facet_grid(x=\"year\") + \\\n",
" ylab(\"mean temperature\") + \\\n",
" ggtitle(\"Annual Path of Mean Temperature and Humidity\") + \\\n",
" ggsize(1000, 500) + \\\n",
" theme_classic()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Autocorrelation Plots for Mean Temperature, Wind Speed and Humidity"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"execution": {
"iopub.execute_input": "2024-03-26T14:41:13.552371Z",
"iopub.status.busy": "2024-03-26T14:41:13.552243Z",
"iopub.status.idle": "2024-03-26T14:41:13.787129Z",
"shell.execute_reply": "2024-03-26T14:41:13.786810Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"acf_df = pd.DataFrame([\n",
" (lag, df[\"mean temperature\"].autocorr(lag=lag), df[\"wind speed\"].autocorr(lag=lag), df.humidity.autocorr(lag=lag))\n",
" for lag in range(365 * 3)\n",
"], columns=[\"lag\", \"mean temperature acf\", \"wind speed acf\", \"humidity acf\"]).melt(\n",
" id_vars=[\"lag\"],\n",
" value_vars=[\"mean temperature acf\", \"wind speed acf\", \"humidity acf\"],\n",
" var_name=\"acf_type\", value_name=\"acf_value\"\n",
")\n",
"\n",
"ggplot(acf_df, aes(\"lag\", \"acf_value\")) + \\\n",
" geom_point(aes(color=\"acf_value\"), size=3) + \\\n",
" scale_color_gradient(low='#fc8d59', high='#91cf60') + \\\n",
" facet_grid(y=\"acf_type\") + \\\n",
" ylab(\"ACF value\") + \\\n",
" ggtitle(\"Autocorrelation Functions\") + \\\n",
" ggsize(1000, 600) + \\\n",
" theme(legend_position='none')"
]
}
],
"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
}