python机器学习使数据更鲜活的可视化工具Pandas_Alive

安装方法

pip install pandas_alive  # 或者conda install pandas_alive -c conda-forge

使用说明

pandas_alive 的设计灵感来自 bar_chart_race，为方便快速进行动画可视化制作，在数据的格式上需要满足如下条件：

每行表示单个时间段
每列包含特定类别的值
索引包含时间组件（可选）

支持示例展示

水平条形图

import pandas_alivecovid_df = pandas_alive.load_dataset()covid_df.plot_animated(filename=\'examples/perpendicular-example.gif\',perpendicular_bar_func=\'mean\')

垂直条形图比赛

import pandas_alivecovid_df = pandas_alive.load_dataset()covid_df.plot_animated(filename=\'examples/example-barv-chart.gif\',orientation=\'v\')

条形图

与时间与 x 轴一起显示的折线图类似

import pandas_alivecovid_df = pandas_alive.load_dataset()covid_df.sum(axis=1).fillna(0).plot_animated(filename=\'examples/example-bar-chart.gif\',kind=\'bar\',period_label={\'x\':0.1,\'y\':0.9},enable_progress_bar=True, steps_per_period=2, interpolate_period=True, period_length=200)

饼图

import pandas_alivecovid_df = pandas_alive.load_dataset()covid_df.plot_animated(filename=\'examples/example-pie-chart.gif\',kind=\"pie\",rotatelabels=True,period_label={\'x\':0,\'y\':0})

多边形地理空间图

import geopandasimport pandas_aliveimport contextilygdf = geopandas.read_file(\'data/italy-covid-region.gpkg\')gdf.index = gdf.regiongdf = gdf.drop(\'region\',axis=1)map_chart = gdf.plot_animated(filename=\'examples/example-geo-polygon-chart.gif\',basemap_format={\'source\':contextily.providers.Stamen.Terrain})

多个图表

pandas_alive 支持单个可视化中的多个动画图表。

示例1

import pandas_aliveurban_df = pandas_alive.load_dataset(\"urban_pop\")animated_line_chart = (urban_df.sum(axis=1).pct_change().fillna(method=\'bfill\').mul(100).plot_animated(kind=\"line\", title=\"Total % Change in Population\",period_label=False,add_legend=False))animated_bar_chart = urban_df.plot_animated(n_visible=10,title=\'Top 10 Populous Countries\',period_fmt=\"%Y\")pandas_alive.animate_multiple_plots(\'examples/example-bar-and-line-urban-chart.gif\',[animated_bar_chart,animated_line_chart],title=\'Urban Population 1977 - 2018\', adjust_subplot_top=0.85, enable_progress_bar=True)

示例2

import pandas_alivecovid_df = pandas_alive.load_dataset()animated_line_chart = covid_df.diff().fillna(0).plot_animated(kind=\'line\',period_label=False,add_legend=False)animated_bar_chart = covid_df.plot_animated(n_visible=10)pandas_alive.animate_multiple_plots(\'examples/example-bar-and-line-chart.gif\',[animated_bar_chart,animated_line_chart],enable_progress_bar=True)

示例3

import pandas_aliveimport pandas as pddata_raw = pd.read_csv(\"https://raw.githubusercontent.com/owid/owid-datasets/master/datasets/Long%20run%20life%20expectancy%20-%20Gapminder%2C%20UN/Long%20run%20life%20expectancy%20-%20Gapminder%2C%20UN.csv\")list_G7 = [\"Canada\",\"France\",\"Germany\",\"Italy\",\"Japan\",\"United Kingdom\",\"United States\",]data_raw = data_raw.pivot(index=\"Year\", columns=\"Entity\", values=\"Life expectancy (Gapminder, UN)\")data = pd.DataFrame()data[\"Year\"] = data_raw.reset_index()[\"Year\"]for country in list_G7:data[country] = data_raw[country].valuesdata = data.fillna(method=\"pad\")data = data.fillna(0)data = data.set_index(\"Year\").loc[1900:].reset_index()data[\"Year\"] = pd.to_datetime(data.reset_index()[\"Year\"].astype(str))data = data.set_index(\"Year\")animated_bar_chart = data.plot_animated(period_fmt=\"%Y\",perpendicular_bar_func=\"mean\", period_length=200,fixed_max=True)animated_line_chart = data.plot_animated(kind=\"line\", period_fmt=\"%Y\", period_length=200,fixed_max=True)pandas_alive.animate_multiple_plots(\"examples/life-expectancy.gif\",plots=[animated_bar_chart, animated_line_chart],title=\"Life expectancy in G7 countries up to 2015\",adjust_subplot_left=0.2, adjust_subplot_top=0.9, enable_progress_bar=True)

示例4

import geopandasimport pandas as pdimport pandas_aliveimport contextilyimport matplotlib.pyplot as pltimport urllib.request, jsonwith urllib.request.urlopen(\"https://data.nsw.gov.au/data/api/3/action/package_show?id=aefcde60-3b0c-4bc0-9af1-6fe652944ec2\") as url:data = json.loads(url.read().decode())# Extract url to csv componentcovid_nsw_data_url = data[\"result\"][\"resources\"][0][\"url\"]# Read csv from data API urlnsw_covid = pd.read_csv(covid_nsw_data_url)postcode_dataset = pd.read_csv(\"data/postcode-data.csv\")# Prepare data from NSW health datasetnsw_covid = nsw_covid.fillna(9999)nsw_covid[\"postcode\"] = nsw_covid[\"postcode\"].astype(int)grouped_df = nsw_covid.groupby([\"notification_date\", \"postcode\"]).size()grouped_df = pd.DataFrame(grouped_df).unstack()grouped_df.columns = grouped_df.columns.droplevel().astype(str)grouped_df = grouped_df.fillna(0)grouped_df.index = pd.to_datetime(grouped_df.index)cases_df = grouped_df# Clean data in postcode dataset prior to matchinggrouped_df = grouped_df.Tpostcode_dataset = postcode_dataset[postcode_dataset[\'Longitude\'].notna()]postcode_dataset = postcode_dataset[postcode_dataset[\'Longitude\'] != 0]postcode_dataset = postcode_dataset[postcode_dataset[\'Latitude\'].notna()]postcode_dataset = postcode_dataset[postcode_dataset[\'Latitude\'] != 0]postcode_dataset[\'Postcode\'] = postcode_dataset[\'Postcode\'].astype(str)# Build GeoDataFrame from Lat Long dataset and make map chartgrouped_df[\'Longitude\'] = grouped_df.index.map(postcode_dataset.set_index(\'Postcode\')[\'Longitude\'].to_dict())grouped_df[\'Latitude\'] = grouped_df.index.map(postcode_dataset.set_index(\'Postcode\')[\'Latitude\'].to_dict())gdf = geopandas.GeoDataFrame(grouped_df, geometry=geopandas.points_from_xy(grouped_df.Longitude, grouped_df.Latitude),crs=\"EPSG:4326\")gdf = gdf.dropna()# Prepare GeoDataFrame for writing to geopackagegdf = gdf.drop([\'Longitude\',\'Latitude\'],axis=1)gdf.columns = gdf.columns.astype(str)gdf[\'postcode\'] = gdf.indexgdf.to_file(\"data/nsw-covid19-cases-by-postcode.gpkg\", layer=\'nsw-postcode-covid\', driver=\"GPKG\")# Prepare GeoDataFrame for plottinggdf.index = gdf.postcodegdf = gdf.drop(\'postcode\',axis=1)gdf = gdf.to_crs(\"EPSG:3857\") #Web Mercatormap_chart = gdf.plot_animated(basemap_format={\'source\':contextily.providers.Stamen.Terrain},cmap=\'cool\')cases_df.to_csv(\'data/nsw-covid-cases-by-postcode.csv\')from datetime import datetimebar_chart = cases_df.sum(axis=1).plot_animated(kind=\'line\',label_events={\'Ruby Princess Disembark\':datetime.strptime(\"19/03/2020\", \"%d/%m/%Y\"),\'Lockdown\':datetime.strptime(\"31/03/2020\", \"%d/%m/%Y\")},fill_under_line_color=\"blue\",add_legend=False)map_chart.ax.set_title(\'Cases by Location\')grouped_df = pd.read_csv(\'data/nsw-covid-cases-by-postcode.csv\', index_col=0, parse_dates=[0])line_chart = (grouped_df.sum(axis=1).cumsum().fillna(0).plot_animated(kind=\"line\", period_label=False, title=\"Cumulative Total Cases\", add_legend=False))def current_total(values):total = values.sum()s = f\'Total : {int(total)}\'return {\'x\': .85, \'y\': .2, \'s\': s, \'ha\': \'right\', \'size\': 11}race_chart = grouped_df.cumsum().plot_animated(n_visible=5, title=\"Cases by Postcode\", period_label=False,period_summary_func=current_total)import timetimestr = time.strftime(\"%d/%m/%Y\")plots = [bar_chart, line_chart, map_chart, race_chart]from matplotlib import rcParamsrcParams.update({\"figure.autolayout\": False})# make sure figures are `Figure()` instancesfigs = plt.Figure()gs = figs.add_gridspec(2, 3, hspace=0.5)f3_ax1 = figs.add_subplot(gs[0, :])f3_ax1.set_title(bar_chart.title)bar_chart.ax = f3_ax1f3_ax2 = figs.add_subplot(gs[1, 0])f3_ax2.set_title(line_chart.title)line_chart.ax = f3_ax2f3_ax3 = figs.add_subplot(gs[1, 1])f3_ax3.set_title(map_chart.title)map_chart.ax = f3_ax3f3_ax4 = figs.add_subplot(gs[1, 2])f3_ax4.set_title(race_chart.title)race_chart.ax = f3_ax4timestr = cases_df.index.max().strftime(\"%d/%m/%Y\")figs.suptitle(f\"NSW COVID-19 Confirmed Cases up to {timestr}\")pandas_alive.animate_multiple_plots(\'examples/nsw-covid.gif\',plots,figs,enable_progress_bar=True)

总结

Pandas_Alive 是一款非常好玩、实用的动画可视化制图工具，以上就是python机器学习使数据更鲜活的可视化工具Pandas_Alive的详细内容，更多关于python机器学习可视化工具Pandas_Alive的资料请关注脚本之家其它相关文章！

您可能感兴趣的文章:

python解释模型库Shap实现机器学习模型输出可视化
python数据挖掘使用Evidently创建机器学习模型仪表板
在Python文件中指定Python解释器的方法
python机器学习Github已达8.9Kstars模型解释器LIME

目录