COVID19-HK

import plotly.express as px import plotly.graph_objects as go import pandas as pd from io import StringIO import requests

url_enhanced_sur_covid_19_eng = 'https://www.chp.gov.hk/files/misc/enhanced_sur_covid_19_eng.csv' url_large_clusters_eng = 'https://www.chp.gov.hk/files/misc/large_clusters_eng.csv' r = requests.get(url_enhanced_sur_covid_19_eng) df_covid = pd.read_csv(StringIO(r.text)) r = requests.get(url_large_clusters_eng) df_cluster = pd.read_csv(StringIO(r.text)) #Cleaning data # Remove all the capital, non capital confusion df_covid["HK/Non-HK resident"] = df_covid["HK/Non-HK resident"].str.upper() # Convert Date to datetime format df_covid["Report date"] = pd.to_datetime(df_covid["Report date"], infer_datetime_format=True) # Cannot convert due to Asymptomatic entity # df["Date of onset"] = pd.to_datetime(df["Date of onset"], infer_datetime_format=True) ## Second file df_cluster["Case no."] = df_cluster[["Involved case number"]].applymap(lambda x: int(x.split(",")[0])) # df_cluster[["Involved case number count"]] = df_cluster[["Involved case number"]].applymap(lambda x: len(x.split(","))) Done df_cluster2 = pd.merge(df_covid, df_cluster, left_on="Case no.", right_on="Case no.")[["Cluster", "Report date", "Number of cases","Case no."]]

df_column_draw_pie_chart(df_covid,'Gender', 'Gender of the infected').show()

df_column_draw_pie_chart(df_covid, 'HK/Non-HK resident', 'Origin of the infected').show()

df_covid

Case no.int64

1 - 15414

Report datedatetime64[ns]

2020-01-23 00:00:00 - 2022-02-06 00:00:00

2020-01-23T00:00:00.000000

2020-01-24T00:00:00.000000

2020-01-26T00:00:00.000000

2020-01-29T00:00:00.000000

df_column_draw_pie_chart(df_covid, 'Classification*', 'Classification of the cases').show()

df_column_count_line_chart(df_covid, 'Report date', 'Infected People Daily')

df_column_count_line_chart(df_covid, 'Report date', 'Infected People Daily', 'cumsum')

from plotly.subplots import make_subplots # Create figure with secondary y-axis fig = make_subplots(specs=[[{"secondary_y": True}]]) # fig.add_trace(go_df_bubble_chart(df_cluster2,"Report date","Case no.","Number of cases","Cluster", lineName="Big Cluster")) fig.add_trace(go_df_count_plot(df_covid,"Report date", lineName="Total Infected Case",mode="cumsum")) fig.add_trace(go_df_count_plot(df_covid,"Report date", lineName="Daily Infected Case",mode="count"), secondary_y=True) # Add figure title fig.update_layout( title_text="Summary of Hong Kong COVID19 Cases" ) # Set x-axis title fig.update_xaxes(title_text="Date") # Set y-axes titles fig.update_yaxes(title_text="Total Cases", secondary_y=False) fig.update_yaxes(title_text="Daily Cases", secondary_y=True) fig.show()

from plotly.subplots import make_subplots # Create figure with secondary y-axis fig = make_subplots(specs=[[{"secondary_y": True}]]) fig.add_trace(go_df_bubble_chart(df_cluster2,"Report date","Case no.","Number of cases","Cluster", lineName="Big Cluster")) fig.add_trace(go_df_count_plot(df_covid,"Report date", lineName="Total Infected Case",mode="cumsum")) fig.add_trace(go_df_count_plot(df_covid,"Report date", lineName="Daily Infected Case",mode="count"), secondary_y=True) # Add figure title fig.update_layout( title_text="Summary of Hong Kong COVID19 Cases" ) # Set x-axis title fig.update_xaxes(title_text="Date") # Set y-axes titles fig.update_yaxes(title_text="Total Cases", secondary_y=False) fig.update_yaxes(title_text="Daily Cases", secondary_y=True) fig.show()