sds-3.x/ScaDaMaLe

pip install plotly

"./DataPreprocess"

display(df_cleaned_time_series.select($"reproduction_rate", $"location", $"date").filter($"reproduction_rate".isNotNull).filter(
                                                                                       $"location"==="Sweden" ||
                                                                                       $"location"==="Germany" ||
                                                                                       $"location"==="Danmark" ||
                                                                                       $"location"==="Finland" ||
                                                                                       $"location"==="Norway").sort("date"))

df_cleaned_time_series.createOrReplaceTempView("visual_rdd")

import pandas as pd
import numpy as np
import plotly.express as px

test_table = spark.table("visual_rdd")

country = np.array(test_table.select("iso_code").rdd.map(lambda l: l[0]).collect())
dates = np.array(test_table.select("date").rdd.map(lambda l: l[0]).collect())
total_cases = np.array(test_table.select("total_cases").rdd.map(lambda l: l[0]).collect())
total_deaths = np.array(test_table.select("total_deaths").rdd.map(lambda l: l[0]).collect())
new_cases = np.array(test_table.select("new_cases").rdd.map(lambda l: l[0]).collect())
new_deaths = np.array(test_table.select("new_deaths").rdd.map(lambda l: l[0]).collect())

visual_data = {'country':country.tolist(), 'total_cases':total_cases, 'date':dates,
             'total_deaths': total_deaths, 'new_cases': new_cases, 'new_deaths': new_deaths}
visual_df = pd.DataFrame(data = visual_data).sort_values(by='date')
visual_df

fig = px.choropleth(visual_df[~visual_df.country.str.contains("WLD", na=False)], locations="country",
                     color="total_cases", # total_cases is a column of gapminder
                     hover_name="country", # column to add to hover information
                     color_continuous_scale=px.colors.sequential.Plasma,
                     animation_frame = 'date')
fig.show()

fig = px.choropleth(visual_df[~visual_df.country.str.contains("WLD", na=False)], locations="country",
                    color="total_deaths", # total_deaths is a column of gapminder
                    hover_name="country", # column to add to hover information
                    color_continuous_scale=px.colors.sequential.Plasma,
                    animation_frame = 'date')
fig.show()

fig = px.choropleth(visual_df[~visual_df.country.str.contains("WLD", na=False)], locations="country",
                    color="new_cases", # new_cases is a column of gapminder
                    hover_name="country", # column to add to hover information
                    color_continuous_scale=px.colors.sequential.Plasma,
                    animation_frame = 'date')
fig.show()

fig = px.choropleth(visual_df[~visual_df.country.str.contains("WLD", na=False)], locations="country",
                    color="new_deaths", # new_deaths is a column of gapminder
                    hover_name="country", # column to add to hover information
                    color_continuous_scale=px.colors.sequential.Plasma,
                    animation_frame = 'date')
fig.show()