TSSFL Stack Live ShowCase During Sabasaba International Trade Fair In Dar Es Salaam, Tanzania

[Eli]

TSSFL ODF Live ShowCase During Sabasaba International Trade Fair In Dar Es Salaam, Tanzania, From 28th June - 13th July 2021

Visualizing the Global 2019 GDP Per Capita, Life Expectancy, and other Social Factors Dataset

Below we show how to use the data science tools, in particular, Python programming language to visualize the relationship between economic and social factors. We use this dataset which features GDP per capita, social support, healthy life expectancy, freedom to make choices, generosity, and so on, all over the world. Run the code below:

Code: [Select all] [Expand/Collapse]

1. import numpy as np
2. import pandas as pd
3. import seaborn as sns
4. import matplotlib.pyplot as plt
5.  
6. #We use the dataset called "2019.csv" found at https://github.com/fati8999-tech/Data-visualization-with-Python-Using-Seaborn-and-Plotly_-GDP-per-Capita-Life-Expectency-Dataset/blob/master/2019.csv
7. #Pull the "raw" GitHub content
8. df = pd.read_csv('https://raw.githubusercontent.com/fati8999-tech/Data-visualization-with-Python-Using-Seaborn-and-Plotly_-GDP-per-Capita-Life-Expectency-Dataset/master/2019.csv')
9. print(df.head(5))
10.  
11. #Configure plotting parameters
12. import seaborn as sns
13. #plt.style.use('ggplot')
14. sns.set_style('darkgrid') # darkgrid, white grid, dark, white and ticks
15. plt.rc('axes', titlesize=18)     # fontsize of the axes title
16. plt.rc('axes', labelsize=14)    # fontsize of the x and y labels
17. plt.rc('xtick', labelsize=13)    # fontsize of the tick labels
18. plt.rc('ytick', labelsize=13)    # fontsize of the tick labels
19. plt.rc('legend', fontsize=13)    # legend fontsize
20. plt.rc('font', size=13)
21.  
22. colors1 = sns.color_palette('pastel')
23. colors2 = sns.color_palette('deep')
24. #colors = sns.color_palette("Set2")
25. #Let's plot a distribution of a single column in a dataframe (GDP per capita)
26. #using sns.distplot(dataofsinglecolumn)
27.  
28. sns.distplot(df['GDP per capita'], bins=10, color="magenta") #Use 10 bins
29. plt.show()
30. plt.clf()
31.  
32. #Let's use 25 bins and remove KDE
33. sns.distplot(df['GDP per capita'], kde = False , bins = 25, color="magenta")
34. plt.show()
35.  
36. #Jointplot
37. #Let's visualize the relationship between two variables using scatter and histogram plots
38.  
39. sns.jointplot(x=df['GDP per capita'], y= df['Healthy life expectancy'],data=df, color="green") #Two ditribution x and y
40. plt.show()
41. plt.clf()
42.  
43. #Let's draw scatter plot using function kind = "", and bin the data into
44. #hexagons with histogram in the margins
45. sns.jointplot(x=df['GDP per capita'], y= df['Healthy life expectancy'],data=df,kind='reg', color=colors2[6])
46. plt.show()
47. plt.clf()
48.  
49. #
50. sns.jointplot(x=df['GDP per capita'], y= df['Healthy life expectancy'],data=df,kind='resid', color=colors1[5])
51. plt.show()
52. plt.clf()
53.  
54. sns.jointplot(x=df['GDP per capita'], y= df['Healthy life expectancy'],data=df,kind='kde', color="purple")
55. plt.show()
56. plt.clf()
57.  
58. sns.jointplot(x=df['GDP per capita'], y= df['Healthy life expectancy'],data=df,kind='hist', color="darkblue")
59. plt.show()
60. plt.clf()
61.  
62. sns.jointplot(x=df['GDP per capita'], y= df['Healthy life expectancy'],data=df,kind='hex', color="red")
63. plt.show()
64. plt.clf()
65.  
66. #Results show that GDP per capita and Healthy life expectancy are positively linearly correlated
67.  
68. df_sorted = df.sort_values('GDP per capita',ascending=False)
69. #Let's plot categorical GDP per capita for top ten countries
70. plt.figure(figsize=(10, 6), tight_layout=True)
71. sns.barplot(x=df_sorted['GDP per capita'],y=df_sorted['Country or region'].head(10),data=df_sorted, color="darkcyan")
72. plt.xticks(rotation=90)
73. plt.title("Top 10 Countries with Highest GDP per Capita")
74. for i, v in enumerate(df_sorted['GDP per capita'].head(10)):
75.     plt.text(v+0.01, i, str(round(v, 4)), color='steelblue', va="center")
76.     plt.text(v+0.3, i, str(i+1), color='black', va="center")
77.  
78. #plt.subplots_adjust(left=0.3)    
79. textstr = 'Created at \nwww.tssfl.com'
80. #plt.text(0.02, 0.5, textstr, fontsize=14, transform=plt.gcf().transFigure)
81. plt.gcf().text(0.02, 0.9, textstr, fontsize=14, color='green') # (0,0) is bottom left, (1,1) is top right
82. plt.show()
83. plt.clf()
84.  
85. df_sorted = df.sort_values('GDP per capita',ascending=False)
86. #Let's plot categorical GDP per capital for top ten countries
87. plt.figure(figsize=(8,6), tight_layout=True)
88. sns.barplot(x=df_sorted['Country or region'].head(10), y=df_sorted['GDP per capita'],data=df_sorted, color="darkcyan")
89. plt.xticks(rotation=90)
90. plt.title("Top 10 Countries with Highest GDP per Capita")
91. xlocs, xlabs = plt.xticks()
92. for i, v in enumerate(df_sorted['GDP per capita'].head(10)):
93.     plt.text(xlocs[i] - 0.25, v + 0.05, str(v), color='steelblue', va="center")
94. plt.gcf().text(0.02, 0.1, textstr, fontsize=14, color='green')
95. plt.show()
96. plt.clf()
97.  
98. #Let's plot categorical GDP per capital for top ten countries
99. df_sorted = df.sort_values('GDP per capita',ascending=True)
100. plt.figure(figsize=(8,8), tight_layout=True)
101. sns.barplot(x=df_sorted['GDP per capita'],y=df_sorted['Country or region'].head(10),data=df_sorted, color="darkmagenta")
102. plt.xticks(rotation=90)
103. plt.title("Countries with Lowest GDP per Capita")
104. for i, v in enumerate(df_sorted['GDP per capita'].head(10)):
105.     plt.text(v+0.01, i, str(round(v, 4)), color='teal', va="center")
106. plt.gcf().text(0.7, 0.85, textstr, fontsize=14, color='green')
107. plt.show()
108. plt.clf()
109.  
110. df_sorted = df.sort_values('GDP per capita',ascending=True)
111. #Let's plot categorical GDP per capital for top ten countries
112. plt.figure(figsize=(8,8), tight_layout=True)
113. sns.barplot(x=df_sorted['Country or region'].head(10), y=df_sorted['GDP per capita'],data=df_sorted, color="darkmagenta")
114. plt.xticks(rotation=90)
115. plt.title("Countries with Lowest GDP per Capita")
116. xlocs, xlabs = plt.xticks()
117. for i, v in enumerate(df_sorted['GDP per capita'].head(10)):
118.     plt.text(xlocs[i] - 0.25, v + 0.01, str(v), color='teal', va="center")
119. plt.gcf().text(0.2, 0.85, textstr, fontsize=14, color='green')
120. plt.show()
121. plt.clf()
122.  
123. df_sorted = df.sort_values('GDP per capita',ascending=True)
124. #Let's plot categorical GDP per capital for top ten countries
125. plt.figure(figsize=(12,40), tight_layout=True)
126. sns.barplot(x=df_sorted['GDP per capita'],y=df_sorted['Country or region'],data=df_sorted, color="lightblue")
127. plt.xticks(rotation=90)
128. plt.title("GDP per Capita")
129. for i, v in enumerate(df_sorted['GDP per capita']):
130.     plt.text(v+0.01, i, str(round(v, 4)), color='teal', va="center")
131.     plt.text(v+0.15, i, str(157-(i+1)), color='black', va="center")
132. plt.gcf().text(0.55, 0.96, textstr, fontsize=14, color='green')
133. plt.show()
134. plt.clf()
135.  
136. df_sorted = df.sort_values('GDP per capita',ascending=False)
137. #Let's plot categorical GDP per capital for top ten countries
138. plt.figure(figsize=(12,40), tight_layout=True)
139. sns.barplot(x=df_sorted['GDP per capita'],y=df_sorted['Country or region'],data=df_sorted, color="lightblue")
140. plt.xticks(rotation=90)
141. plt.title("GDP per Capita")
142. for i, v in enumerate(df_sorted['GDP per capita']):
143.     plt.text(v+0.01, i, str(round(v, 4)), color='teal', va="center")
144.     plt.text(v+0.15, i, str(i+1), color='black', va="center")
145. plt.gcf().text(0.02, 0.99, textstr, fontsize=14, color='green')
146. plt.show()
147. plt.clf()
148. #End
149.  
150. #Let's plot categorical GDP per capital for top ten countries
151. plt.figure(figsize=(8,5), tight_layout=True)
152. sns.barplot(x=df['Country or region'].tail(10),y=df['GDP per capita'],data=df, color="olive")
153. plt.xticks(rotation=90)
154. plt.show()
155. plt.clf()
156.  
157. #Matrix plot visualizing correlation btn the data selected
158. data_select = df[['GDP per capita','Social support','Healthy life expectancy','Perceptions of corruption']]
159. print("Correlation between Data:")
160. print(data_select.corr())
161.  
162. #Visualize
163. #Change color as you want https://matplotlib.org/tutorials/colors/colormaps.html
164. plt.figure(figsize=(8,6), tight_layout=True)
165. sns.heatmap(data_select.corr(), cmap='coolwarm')
166. plt.title("Matrix Plot")
167. plt.show()
168. plt.clf()
169.  
170. #Let's get various relationships for the entire dataset
171. #Get the distribution of a single variable by hist and of two variables by scatter
172. plt.style.use('ggplot')
173. sns.pairplot(df)
174. plt.show()
175. plt.clf()

[Eli]

Here is the output:

[Eli]

Related news:

https://udsm.ac.tz/web/index.php/colleg ... dift)-2021

[Eli]

Here is the related analysis

Code: [Select all] [Expand/Collapse]

1. import pandas as pd
2. import matplotlib.pyplot as plt
3.  
4. data = pd.read_csv('https://raw.githubusercontent.com/mpicbg-scicomp/dlbc17-python-intro/master/data/gapminder_gdp_oceania.csv', index_col='country')
5.  
6. # Extract year from last 4 characters of each column name
7. # The current column names are structured as 'gdpPercap_(year)',
8. # so we want to keep the (year) part only for clarity when plotting GDP vs. years
9. # To do this we use strip(), which removes from the string the characters stated in the argument
10. # This method works on strings, so we call str before strip()
11.  
12. years = data.columns.str.strip('gdpPercap_')
13.  
14. # Convert year values to integers, saving results back to dataframe
15.  
16. data.columns = years.astype(int)
17.  
18. data.loc['Australia'].plot()
19. plt.show()
20. plt.clf()
21.  
22. #Select and transform data, then plot it
23. data.T.plot()
24. plt.ylabel('GDP per capita')
25. plt.show()
26.  
27. #Use ggplot
28.  
29. plt.style.use('ggplot')
30. data.T.plot(kind='bar')
31. plt.ylabel('GDP per capita')
32. plt.show()
33. plt.clf()
34.  
35. #Use Matplotlib
36. years = data.columns
37. gdp_australia = data.loc['Australia']
38. plt.plot(years, gdp_australia, 'g--')
39. plt.show()
40.  
41. #Plot several datasets
42. # Select two countries' worth of data.
43. gdp_australia = data.loc['Australia']
44. gdp_nz = data.loc['New Zealand']
45.  
46. # Plot with differently-colored markers.
47. plt.plot(years, gdp_australia, 'b-', label='Australia')
48. plt.plot(years, gdp_nz, 'g-', label='New Zealand')
49.  
50. # Create legend.
51. plt.legend(loc='upper left')
52. plt.xlabel('Year')
53. plt.ylabel('GDP per capita ($)')
54. plt.show()
55. plt.clf()
56.  
57. #Plot a scatter plot correlating the GDP of Australia and New Zealand
58. plt.scatter(gdp_australia, gdp_nz)
59. plt.show()
60. plt.clf()
61. data.T.plot.scatter(x = 'Australia', y = 'New Zealand')
62. plt.show()
63. plt.clf()
64.  
65. #Plot the minimum GDP per capita over time for all the countries in Europe
66. #plot the maximum GDP per capita over time for Europe
67. data_europe = pd.read_csv('https://raw.githubusercontent.com/alistairwalsh/2016-07-13-SUT/master/data/gapminder_gdp_europe.csv', index_col='country')
68. data_europe.min().plot(label='min')
69. data_europe.max().plot(label='max')
70. plt.title("Min and Max GDP per capita: European countries")
71. plt.legend(loc='best')
72. plt.xticks(rotation=90)
73. plt.show()
74. plt.clf()
75.  
76. #Scatter plot showing the relationship between the minimum and maximum GDP per capita among the countries in Asia
77. #for each year in the data set
78. data_asia = pd.read_csv('https://raw.githubusercontent.com/vanzaj/2016-06-11-ntu/gh-pages/data/gapminder_gdp_asia.csv', index_col='country')
79. data_asia.describe().T.plot(kind='scatter', x='min', y='max')
80. plt.title("Min and Max GDP per capita: Asia countries")
81. plt.show()
82. plt.clf()
83. #No particular correlations can be seen between the minimum and maximum gdp values year on year
84.  
85. #The variability in the maximum is much higher than that of the minimum
86. data_asia.max().plot()
87. print(data_asia.idxmax())
88. print(data_asia.idxmin())
89. plt.title("Variability in max and min GDP per capita: Asia")
90. plt.xticks(rotation=90)
91. plt.show()
92. #Myanmar consistently has the lowest gdp, the highest gdb nation has varied more notably
93. plt.clf()
94.  
95. #The correlation between GDP and life expectancy for 2007, normalizing marker size by population:
96. data_all = pd.read_csv('https://raw.githubusercontent.com/mpicbg-scicomp/dlbc17-python-intro/master/data/gapminder_all.csv', index_col='country')
97. data_all.plot(kind='scatter', x='gdpPercap_2007', y='lifeExp_2007',
98.               s=data_all['pop_2007']/1e6)
99. plt.title("Correlation btn GDP and life expectancy for 2007")
100. plt.show()

Ref: [1]

[Eli]

We can do similar analysis with R

Code: [Select all] [Expand/Collapse]

1. #googlesheets4 auth
2. #library(googlesheets4)
3. #read_sheet("https://docs.google.com/spreadsheets/d/1BC48PKPZW71AC6hOn1SNesvZk1PoBjE4wXwl1YlWFpY/edit#gid=0")
4. #read_sheet("https://docs.google.com/spreadsheets/d/1U6Cf_qEOhiR9AZqTqS3mbMF3zt2db48ZP5v3rkrAEJY/edit#gid=780868077")
5. #read_sheet("1U6Cf_qEOhiR9AZqTqS3mbMF3zt2db48ZP5v3rkrAEJY")
6.  
7. library(googlesheets4)
8. #gs4_deauth()
9. gs4_deauth()
10. #Imagine this is the URL or ID of a Sheet readable by anyone (with a link)
11. ss <- "https://docs.google.com/spreadsheets/d/1U6Cf_qEOhiR9AZqTqS3mbMF3zt2db48ZP5v3rkrAEJY/edit#gid=780868077"
12. dat <- read_sheet(ss)
13.  
14. #By sheet ID
15. ss2 <- "1U6Cf_qEOhiR9AZqTqS3mbMF3zt2db48ZP5v3rkrAEJY"
16. dat2 <- read_sheet(ss2)

See documentation: Ref1, Ref2

See basic usage:

https://cran.r-project.org/web/packages ... usage.html