pip install wbdata

pip install wbdata==0.2.0

pip install wbdata==0.2.0 import wbdata import pandas as pd import datetime # Set the start and end date for the data start_date = datetime.datetime(2020, 1, 1) end_date = datetime.datetime(2020, 12, 31) # Define the indicators for patent applications by residents and non-residents indicators = {'IP.PAT.RESD': 'Patents by residents', 'IP.PAT.NRES': 'Patents by non-residents'} # Set the countries for which you want to retrieve data countries = ['USA', 'CAN'] # Retrieve the data from the World Bank API patents_data = wbdata.get_dataframe(indicators, country=countries, data_date=(start_date, end_date), convert_date=True) # Reset the index to make 'date' a column patents_data.reset_index(inplace=True) # Create a new variable showing the total patents for each country patents_data['Total_Patents'] = patents_data['Patents by residents'] + patents_data['Patents by non-residents'] # Display the resulting DataFrame print(patents_data.head())

import matplotlib.pyplot as plt # Assuming you have a DataFrame named 'patents_data' with columns 'Country', 'GDP_Per_Capita', 'Total_Patents', and 'Year' # Filter data for the specified years selected_years = [1990, 1995, 2000, 2010, 2020] selected_data = patents_data[patents_data['Year'].isin(selected_years)] # Plot the relation between GDP per capita and total patents using your custom function (my_xy_plot) for year in selected_years: data_for_year = selected_data[selected_data['Year'] == year] # Assuming my_xy_plot takes x, y, title, xlabel, ylabel as parameters my_xy_plot(data_for_year['GDP_Per_Capita'], data_for_year['Total_Patents'], title=f'Relation between GDP per capita and Total Patents ({year})', xlabel='GDP per Capita', ylabel='Total Patents') # Show the plot (optional) plt.show()

import seaborn as sns import matplotlib.pyplot as plt # Assuming you have a DataFrame named 'patents_data' with columns 'Country', 'GDP_Per_Capita', 'Total_Patents', 'Income_Group', 'Region', and 'Year' # Select relevant columns selected_columns = ['Country', 'GDP_Per_Capita', 'Total_Patents', 'Income_Group', 'Region', 'Year'] # Filter data for selected columns selected_data = patents_data[selected_columns] # Separate figures for GDP per capita and total patents by income groups plt.figure(figsize=(12, 8)) sns.set_palette("husl") # GDP per capita by income group sns.lineplot(x='Year', y='GDP_Per_Capita', hue='Income_Group', data=selected_data) plt.title('Evolution of GDP per Capita by Income Group') plt.xlabel('Year') plt.ylabel('GDP per Capita') plt.legend(loc='best') plt.grid(True) plt.savefig('./graphs/gdp_per_capita_by_income_group.png') plt.show() # Total patents by income group plt.figure(figsize=(12, 8)) sns.set_palette("husl") sns.lineplot(x='Year', y='Total_Patents', hue='Income_Group', data=selected_data) plt.title('Evolution of Total Patents by Income Group') plt.xlabel('Year') plt.ylabel('Total Patents') plt.legend(loc='best') plt.grid(True) plt.savefig('./graphs/total_patents_by_income_group.png') plt.show() # Separate figures for GDP per capita and total patents by region plt.figure(figsize=(12, 8)) sns.set_palette("husl") # GDP per capita by region sns.lineplot(x='Year', y='GDP_Per_Capita', hue='Region', data=selected_data) plt.title('Evolution of GDP per Capita by Region') plt.xlabel('Year') plt.ylabel('GDP per Capita') plt.legend(loc='best') plt.grid(True) plt.savefig('./graphs/gdp_per_capita_by_region.png') plt.show() # Total patents by region plt.figure(figsize=(12, 8)) sns.set_palette("husl") sns.lineplot(x='Year', y='Total_Patents', hue='Region', data=selected_data) plt.title('Evolution of Total Patents by Region') plt.xlabel('Year') plt.ylabel('Total Patents') plt.legend(loc='best') plt.grid(True) plt.savefig('./graphs/total_patents_by_region.png') plt.show()

import matplotlib.pyplot as plt # Assuming you have a DataFrame named 'patents_data' with columns 'Country', 'Patents_by_Residents', 'Patents_by_NonResidents', and 'Year' # Filter data for the year 2015 data_2015 = patents_data[patents_data['Year'] == 2015] # Create a scatter plot plt.figure(figsize=(10, 8)) plt.scatter(data_2015['Patents_by_Residents'], data_2015['Patents_by_NonResidents'], alpha=0.7) # Show the 45-degree line plt.plot([0, max(data_2015['Patents_by_Residents'])], [0, max(data_2015['Patents_by_Residents'])], color='red', linestyle='--') plt.title('Relation between Patenting Activity by Residents and Non-Residents (2015)') plt.xlabel('Patents by Residents') plt.ylabel('Patents by Non-Residents') plt.grid(True) plt.show()

import geopandas as gpd import matplotlib.pyplot as plt # Assuming you have a GeoDataFrame named 'world' with geometry and a DataFrame named 'patents_data' with columns 'Country' and 'Patents_2015' # Merge the GeoDataFrame with patent data world_patents = world.merge(patents_data, how='left', left_on='ISO_A3', right_on='Country') # Create a static map fig, ax = plt.subplots(1, 1, figsize=(15, 10)) world_patents.boundary.plot(ax=ax, linewidth=0.8) world_patents.plot(column='Patents_2015', cmap='YlGnBu', linewidth=0.8, ax=ax, legend=True, legend_kwds={'label': "Patents 2015 by Country", 'orientation': "horizontal"}) plt.title('Patenting Activity Across the World (2015)') plt.show()

import plotly.express as px # Assuming you have a DataFrame named 'patents_data' with columns 'Country', 'Patents_2015', 'Latitude', and 'Longitude' # Create a dynamic map fig = px.scatter_geo(patents_data, locations="Country", locationmode="country names", color="Patents_2015", size="Patents_2015", hover_name="Country", size_max=50, projection="natural earth", title='Patenting Activity Across the World (2015)') fig.show()

pip install geopandas matplotlib plotly import pandas as pd import seaborn as sns import matplotlib.pyplot as plt # Assuming you have a DataFrame named 'patents_data' with columns 'Country', 'Log_GDP_Per_Capita', 'Patents_by_Residents', 'Patents_by_NonResidents', 'Total_Patents' # Create a new DataFrame for the table table_data = patents_data[['Country', 'Log_GDP_Per_Capita', 'Patents_by_Residents', 'Patents_by_NonResidents', 'Total_Patents']] # Display the table print(table_data) # Create scatter plots plt.figure(figsize=(15, 8)) # Scatter plot for residents plt.subplot(2, 2, 1) sns.scatterplot(x='Log_GDP_Per_Capita', y='Patents_by_Residents', data=table_data) plt.title('Residents Patents vs Log GDP per Capita') # Scatter plot for non-residents plt.subplot(2, 2, 2) sns.scatterplot(x='Log_GDP_Per_Capita', y='Patents_by_NonResidents', data=table_data) plt.title('Non-Residents Patents vs Log GDP per Capita') # Scatter plot for total patents plt.subplot(2, 2, 3) sns.scatterplot(x='Log_GDP_Per_Capita', y='Total_Patents', data=table_data) plt.title('Total Patents vs Log GDP per Capita') # Scatter plot for all three on one figure plt.subplot(2, 2, 4) sns.scatterplot(x='Log_GDP_Per_Capita', y='Patents_by_Residents', data=table_data, label='Residents', color='blue', alpha=0.7) sns.scatterplot(x='Log_GDP_Per_Capita', y='Patents_by_NonResidents', data=table_data, label='Non-Residents', color='orange', alpha=0.7) sns.scatterplot(x='Log_GDP_Per_Capita', y='Total_Patents', data=table_data, label='Total', color='green', alpha=0.7) plt.title('Patents vs Log GDP per Capita') plt.legend() plt.tight_layout() plt.show()