Dataset variables originales
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
dataset = pd.read_csv("ds3.csv", delimiter=",")
dataset
sns.pairplot(data=dataset)
plt.savefig("correlations_originalvariables.png")
plt.show()
Dataset variables del modelo final
dataset_final = pd.read_csv("ds4.csv", delimiter=",")
dataset_final
sns.pairplot(data=dataset_final)
plt.savefig("correlations_final.png")
plt.show()
Lifeexp
#jointplot chart
sns.jointplot(data=dataset_final, x="GDP", y="lifeexp", kind="scatter")
plt.savefig("joinplotlifexp.png")
plt.show()
sns.boxplot(data=dataset_final,y="lifeexp")
sns.swarmplot(data=dataset_final,y="lifeexp", palette='dark:0')
plt.savefig("lifeexp.png")
plt.show()
VIHprev
sns.boxplot(data=dataset_final,y="VIHprev")
sns.swarmplot(data=dataset_final,y="VIHprev", palette='dark:0')
plt.show()
sns.violinplot(data=dataset_final,y="VIHprev")
plt.savefig("violinVIH.png")
plt.show()
GDP
sns.boxplot(data=dataset_final,y="GDP")
sns.swarmplot(data=dataset_final,y="GDP", palette='dark:0')
plt.savefig("GDP.png")
plt.show()
Adolescent Fertility
sns.boxplot(data=dataset_final,y="adolecent_fert")
sns.swarmplot(data=dataset_final,y="adolecent_fert", palette='dark:0')
plt.savefig("Adolescent.png")
plt.show()
Neonat_Mortal
sns.boxplot(data=dataset_final,y="neonat_Mortal")
sns.swarmplot(data=dataset_final,y="neonat_Mortal", palette='dark:0')
plt.savefig("Neonat.png")
plt.show()
Population
dataset_population = pd.read_csv("data.csv", delimiter=",")
dataset_population
sns.boxplot(data=dataset_population,y="POP")
sns.swarmplot(data=dataset_population,y="POP", palette='dark:0')
plt.show()
print(dataset_population.POP.median())
sns.histplot(data=dataset_population, x="POP")
plt.savefig("Population.png")
plt.plot()
Relación entre esperanza de vida y PIB
#graficos
plt.scatter(dataset_population["GDP"], dataset_population["lifeexp"],
c = (dataset_population["POP"]/1366417756),
s=(dataset_population["POP"]*0.000001)
)
#nombres en los puntos (seleccionados)
plt.text(x=dataset_population.GDP[dataset_population["Pais"]=='India']+5000,
y=dataset_population.lifeexp[dataset_population["Pais"]=='India'],
s="India",
fontdict=dict(color="black",size=10))
plt.text(x=dataset_population.GDP[dataset_population["Pais"]=='United States']+5000,
y=dataset_population.lifeexp[dataset_population["Pais"]=='United States']+0.3,
s="USA",
fontdict=dict(color="black",size=10))
plt.text(x=dataset_population.GDP[dataset_population["Pais"]=='Brazil'],
y=dataset_population.lifeexp[dataset_population["Pais"]=='Brazil'],
s="Brasil",
fontdict=dict(color="black",size=10))
plt.text(x=dataset_population.GDP[dataset_population["Pais"]=='Luxembourg']-17000,
y=dataset_population.lifeexp[dataset_population["Pais"]=='Luxembourg']+1,
s="Luxemburgo",
fontdict=dict(color="black",size=10))
plt.text(x=dataset_population.GDP[dataset_population["Pais"]=='Chad']+1000,
y=dataset_population.lifeexp[dataset_population["Pais"]=='Chad']-0.5,
s="Chad",
fontdict=dict(color="black",size=10))
#labels y barra de color
plt.colorbar(label="Población")
plt.xlabel("PIB Per Cápita, dólares estadounidenses ajustados a PPA")
plt.ylabel("Esperanza de vida")
plt.savefig("LifeexpvsGDPPRO.png")
plt.show()