Plotting High Quality Plots in Python with Plotly and Clufflinks¶

import pandas as pd
import numpy as np
import warnings
from plotly.offline import init_notebook_mode, iplot
import plotly.figure_factory as ff
import cufflinks
import plotly.io as pio 
cufflinks.go_offline()
cufflinks.set_config_file(world_readable=True, theme='pearl')
pio.renderers.default = "colab" # should change by looking into pio.renderers

pd.options.display.max_columns = None
# pd.options.display.max_rows = None

pio.renderers

df = pd.read_csv("https://covid.ourworldindata.org/data/owid-covid-data.csv")
df["date"] = pd.to_datetime(df.date)
df

total = df.isnull().sum().sort_values(ascending = False)
percent = (df.isnull().sum()/df.isnull().count()).sort_values(ascending = False)
mdf = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
mdf = mdf.reset_index()
mdf

mdf.query("Total>100000").iplot(kind='pie',labels = "index", 
                                values="Total", textinfo="percent+label",
                                title='Top Columns with Missing Values', hole = 0.5)

mdf.query("Total>100000").iplot(kind='pie',labels = "index", 
                                values="Total",
                                title='Top Columns with Missing Values', hole = 0.5)

todf = df[~df.location.isin(["Lower middle income", "North America", "World", "Asia", "Europe", 
                           "European Union", "Upper middle income", 
                           "High income", "South America"])]
tdf = todf.groupby("date").aggregate(new_cases=("new_cases", "sum"),
                                   new_deaths = ("new_deaths", "sum"),
                                   new_vaccinations = ("new_vaccinations", "sum"),
                                   new_tests = ("new_tests", "sum")
                                   ).reset_index()

tdf.iplot(kind="line",
          y="new_cases",
          x="date",
          xTitle="Date",
          width=2,
          yTitle="new_cases", 
          title="New Cases from Jan 2020 to Jan 2022")

tdf.iplot(kind="line",
          y=["new_deaths", "new_vaccinations", "new_tests"],
          x="date",
          xTitle="Date",
          width=2,
          yTitle="Cases", 
          title="Cases from Jan 2020 to Jan 2022")

tdf.iplot(kind="line",
          y=["new_deaths", "new_vaccinations", "new_tests"],
          x="date",
          xTitle="Date",
          width=2,
          yTitle="Cases", 
          subplots=True,
          title="Cases from Jan 2020 to Jan 2022")

tdf.iplot(kind="line",
          y=["new_vaccinations"],
          secondary_y = "new_tests",
          x="date",
          xTitle="Date",
          width=2,
          yTitle="new_vaccinations",
          secondary_y_title="new_tests", 
          title="Cases from Jan 2020 to Jan 2022")

tdf.iplot(kind="scatter",
              y="new_deaths", x='new_cases',
              mode='markers',
              yTitle="New Deaths", xTitle="New Cases",
              title="New Deaths vs New Cases")

tdf.iplot(kind="scatter",
              x="new_deaths", y='new_cases',
              secondary_y="new_tests",
              secondary_y_title="New Tests",
              mode='markers',
              xTitle="New Deaths", yTitle="New Cases",
              title="New Deaths vs New Cases")

tdf.iplot(kind="scatter",
              x="new_deaths", y='new_cases',
              secondary_y="new_tests",
              secondary_y_title="New Tests",
              mode='markers',
              subplots=True,
              xTitle="New Deaths", yTitle="New Cases",
              title="New Deaths vs New Cases")

topdf.iplot(kind="bar", x="location",
                                      y="total_deaths",
                                      theme="polar",
                                      xTitle="Countries", yTitle="Total Deaths", 
                                       title="Top 20 Countries according to total deaths")

topdf.iplot(kind="bar", x="location",
            y="total_deaths",
            theme="polar", orientation='h',
            xTitle="Countries", yTitle="Total Deaths", 
            title="Top 20 Countries according to total deaths")

topdf.iplot(kind="bar", x="location",
            y=["total_deaths", "total_cases", "total_tests"],
            theme="polar",
            xTitle="Countries", yTitle="Total Deaths", 
            title="Top 20 Countries according to total deaths")

topdf.iplot(kind="bar", x="location",
                        y=["total_deaths", "total_cases", "total_tests"],
                        theme="polar",
                        barmode="overlay",
                        xTitle="Countries", yTitle="Total Deaths", 
                        title="Top 20 Countries according to total deaths")

topdf.iplot(kind="bar", x="location",
                        y=["total_deaths", "total_cases", "total_tests"],
                        theme="polar",
                        barmode="overlay",
                        xTitle="Countries", yTitle="Total Deaths", 
                        subplots=True,
                        title="Top 20 Countries according to total deaths")

tdf.iplot(kind="hist",
              bins=50, 
              colors=["red"],
              keys=["total_tests"],
              title="Total tests Histogram")

tdf.iplot(kind="hist",
              bins=100, 
              colors=["red"],
              keys=["total_tests", "total_cases", "total_deaths"],
              title="Multiple Histogram")

tdf.iplot(kind="hist",
              subplots=True,
              keys=["total_tests", "total_cases", "total_deaths"],
              title="Multiple Histogram")

tdf.iplot(kind="box",
              keys=["total_tests", "total_cases", "total_deaths"], 
              boxpoints="outliers",
              x="location",
              xTitle="Columns", title="Box Plot Tests, Cases and Deaths")

tdf.iplot(kind="box",
              keys=["total_tests", "total_cases", "total_deaths"], 
              boxpoints="outliers",
              x="location",
              subplots=True,
              xTitle="Columns", title="Box Plot Tests, Cases and Deaths")

df[["new_cases", "new_deaths", "new_tests"]].corr().iplot(kind="heatmap")

import plotly.graph_objects as go

ldf = df[~df.location.isin(["Lower middle income", "North America", "World", "Asia", "Europe", 
                           "European Union", "Upper middle income", 
                           "High income", "South America"])].drop_duplicates("location", keep="last") 

fig = go.Figure(data=go.Choropleth(
    locations = ldf['iso_code'],
    z = ldf['total_deaths'],
    text = ldf['location'],
    colorscale = 'Blues',
    autocolorscale=False,
    reversescale=True,
    marker_line_color='darkgray',
    marker_line_width=0.5,
    colorbar_title = 'total_deaths',
))

fig.update_layout(
    title_text='total_deaths vs Country',
    geo=dict(
        showframe=False,
        showcoastlines=False,
        projection_type='equirectangular'
    )
)

fig.show()

tldf = df[~df.location.isin(["Lower middle income", "North America", "World", "Asia", "Europe", 
                           "European Union", "Upper middle income", 
                           "High income", "South America"])]
tldf = tldf.groupby(["location", "iso_code", pd.Grouper(key="date", freq="1M")]).aggregate(total_cases=("total_cases", "max")).reset_index()
tldf["date"] = tldf["date"].dt.date
tldf

first_day = tldf.date.min()

scl = [[0.0, '#ffffff'],[0.2, '#b4a8ce'],[0.4, '#8573a9'],
       [0.6, '#7159a3'],[0.8, '#5732a1'],[1.0, '#2c0579']] # purples

data_slider = []
for date in tldf['date'].unique():
    df_segmented =  tldf[(tldf['date']== date)]

    for col in df_segmented.columns:
        df_segmented[col] = df_segmented[col].astype(str)

    data_each_yr = dict(
                        type='choropleth',
                        locations = df_segmented['iso_code'],
                        z=df_segmented["total_cases"].astype(float),
                        colorbar= {'title':'Total Cases'}
                        )

    data_slider.append(data_each_yr)

steps = []
for i,date in enumerate(tldf.date.unique()):
    step = dict(method='restyle',
                args=['visible', [False] * len(data_slider)],
                label='Date {}'.format(date))
    step['args'][1][i] = True
    steps.append(step)

sliders = [dict(active=0, pad={"t": 1}, steps=steps)]

layout = dict(title ='Total Cases at the End of Month Across the World',
              sliders=sliders)

fig = dict(data=data_slider, layout=layout)
iplot(fig)

tldf.head()

import plotly.express as px


fig = px.density_mapbox(tldf.drop_duplicates(keep="last"), 
                          lat = tldf["lat"],
                          lon = tldf["lon"],
                          hover_name="location", 
                          hover_data=["total_cases"], 
                          color_continuous_scale="Portland",
                          radius=7, 
                          zoom=0,
                          height=700,
                          z="total_cases"
                          )
fig.update_layout(title=f'Country vs total_cases',
                  font=dict(family="Courier New, monospace",
                            size=18,
                            color="#7f7f7f")
                )
fig.update_layout(mapbox_style="open-street-map", mapbox_center_lon=0)


fig.show()

first_day = tldf.date.min()

scl = [[0.0, '#ffffff'],[0.2, '#b4a8ce'],[0.4, '#8573a9'],
       [0.6, '#7159a3'],[0.8, '#5732a1'],[1.0, '#2c0579']] # purples

data_slider = []
for date in tldf['date'].unique():
    df_segmented =  tldf[(tldf['date']== date)]

    for col in df_segmented.columns:
        df_segmented[col] = df_segmented[col].astype(str)

    data_each_yr = dict(
                        type='densitymapbox',
                        lat = df_segmented["lat"],
                        lon = df_segmented["lon"],
                        hoverinfo="text",
                        # name = "country",
                        text = df_segmented["country"],                        
                        z=df_segmented["total_cases"].astype(float),
                        colorbar= {'title':'Total Cases'}
                        )

    data_slider.append(data_each_yr)

steps = []
for i,date in enumerate(tldf.date.unique()):
    step = dict(method='restyle',
                args=['visible', [False] * len(data_slider)],
                label='Date {}'.format(date))
    step['args'][1][i] = True
    steps.append(step)

sliders = [dict(active=0, pad={"t": 1}, steps=steps)]

layout = dict(mapbox_style="open-street-map",
              title ='Total Cases at the End of Month Across the World',
              sliders=sliders)

fig = dict(data=data_slider, layout=layout)

iplot(fig)