Geopandas: how to plot countries/cities?

From the code you've posted I can't see anything wrong with the plotting, so I assume that the issue might be somewhere in your data aggregation or merging.

Here is a solution that starts by generating data which should be similar to yours, then counts the number of times a country appears in the data as a proportion of the size of the dataset, as this is the required metric. We'll focus on just using a few countries as an example:

from random import choices
import pandas as pd
import numpy as np

def generate_data():
    
    k = 100
    
    countries_of_interest = ['USA','ARG','BRA','GBR','ESP','RUS']
    countries = choices(countries_of_interest, k=k)
    
    start_yr = 2010
    end_yr = 2021
    
    return pd.DataFrame({'Country':countries, 
                         'Year':np.random.randint(start_yr, end_yr, k)},
                        index=range(len(countries)))


def aggregate_data(df):
    data = df.groupby('Country').agg('count')*100.0/len(df)
    data = data.reset_index().rename(columns={'Year':'proportion_of_dataset'})
    return data

df = generate_data()

#    Country  Year
# 0      USA  2017
# 1      GBR  2014
# 2      USA  2013
# 3      BRA  2016
# 4      BRA  2018
# ..     ...   ...
# 95     ESP  2014
# 96     USA  2015
# 97     RUS  2019
# 98     RUS  2012
# 99     RUS  2011
# 
# [100 rows x 2 columns]

data = aggregate_data(df)

#   Country  proportion_of_dataset
# 0     ARG                   20.0
# 1     BRA                   17.0
# 2     ESP                   14.0
# 3     GBR                   14.0
# 4     RUS                   19.0
# 5     USA                   16.0

Now load the country border shapefile using geopandas, and rename columns:

import geopandas as gpd

shapefile = 'path_to_shapfile_folder/ne_110m_admin_0_countries/ne_110m_admin_0_countries.shp'
gdf = gpd.read_file(shapefile)[['ADMIN', 'ADM0_A3', 'geometry']]
gdf.columns = ['country', 'country_code', 'geometry']

gdf.head()

#                        country country_code  \
# 0                         Fiji          FJI   
# 1  United Republic of Tanzania          TZA   
# 2               Western Sahara          SAH   
# 3                       Canada          CAN   
# 4     United States of America          USA   
# 
#                                             geometry  
# 0  MULTIPOLYGON (((180.00000 -16.06713, 180.00000...  
# 1  POLYGON ((33.90371 -0.95000, 34.07262 -1.05982...  
# 2  POLYGON ((-8.66559 27.65643, -8.66512 27.58948...  
# 3  MULTIPOLYGON (((-122.84000 49.00000, -122.9742...  
# 4  MULTIPOLYGON (((-122.84000 49.00000, -120.0000...

Now we want to merge the country polygon dataframe with our aggregated data. Note: we want to do a left join (on the full country polygon dataframe) so that we include all countries, even ones we don't have data for. Also note that we are adding missing values for these countries by filling NaNs with zeros:

merged = gdf.merge(data, left_on = 'country_code', right_on = 'Country', how='left')
merged['proportion_of_dataset'] = merged['proportion_of_dataset'].fillna(0)

Using your code to create the geojson:

import json

merged_json = json.loads(merged.to_json())
json_data = json.dumps(merged_json)

Finally, we'll put your plotting code in a function, and pass in as arguments the geojson, column to plot, and the plot title:

from bokeh.io import output_notebook, show, output_file
from bokeh.plotting import figure
from bokeh.models import GeoJSONDataSource, LinearColorMapper, ColorBar
from bokeh.palettes import brewer

def plot_map(json_data,plot_col,title):

    geosource = GeoJSONDataSource(geojson = json_data)

    #Define a sequential multi-hue color palette.
    palette = brewer['YlGnBu'][8]
    palette = palette[::-1]
    color_mapper = LinearColorMapper(palette = palette, low = 0, high = 40)

    tick_labels = {'0': '0%', '5': '5%', '10':'10%', '15':'15%', '20':'20%', '25':'25%', '30':'30%','35':'35%', '40': '>40%'}

    color_bar = ColorBar(color_mapper=color_mapper, label_standoff=8,width = 500, height = 20,
    border_line_color=None,location = (0,0), orientation = 'horizontal', major_label_overrides = tick_labels)

    p = figure(title = title, plot_height = 600 , plot_width = 950, toolbar_location = None)
    p.xgrid.grid_line_color = None
    p.ygrid.grid_line_color = None

    p.patches('xs','ys', source = geosource,fill_color = {'field' :plot_col, 'transform' : color_mapper},
              line_color = 'black', line_width = 0.25, fill_alpha = 1)

    p.add_layout(color_bar, 'below')

    output_notebook()

    #Display figure.
    show(p)

Now all we have to do is call the plotting function, passing in the required parameters:

plot_map(json_data,'proportion_of_dataset','Dataset countries of origin')