labelproblem

import pandas as pd #tabular data
import numpy as np #numeric operations
import seaborn as sns

import matplotlib.pyplot as plt
import matplotlib.pylab as pylab
#import xlrd as xlrd

pd.set_option('display.max_rows', 10000)
pd.set_option('display.max_columns', 10000)
pd.set_option('display.width', 10000)
 
from matplotlib import pyplot as plt #visualizations
import seaborn as sns
%matplotlib inline


area                     = pd.read_csv("C:/Users/svstu/csv/clean/area_clean.csv",sep=',') 
crime                    = pd.read_csv("C:/Users/svstu/csv/clean/crime_clean.csv",sep=',')
education                = pd.read_csv("C:/Users/svstu/csv/clean/edu_clean.csv",sep=',')
income                   = pd.read_csv("C:/Users/svstu/csv/clean/income_clean.csv",sep=',')
life                     = pd.read_csv("C:/Users/svstu/csv/clean/life_expectancy_clean.csv",sep=',')
region                   = pd.read_csv("C:/Users/svstu/csv/clean/region_clean.csv",sep=',')

df = pd.merge(education, life, how="inner", on="State")
df = pd.merge(df, crime, how="inner", on="State")
df = pd.merge(df, area, how="inner", on="State")
df = pd.merge(df, income, how="inner", on="State")
df = pd.merge(df, region, how="inner", on="State")
# make the variables Region and Division categorical
df["Region"] = pd.Categorical(df["Region"], ordered=False)
df["Division"] = pd.Categorical(df["Division"], ordered=False)
df.head()


#2. Which state has the highest life expectancy and which state the lowest? (lables not correct)

x = np.sort(df['LifeExp2018'])
y = np.arange(1, len(x)+1)/len(x)
z = df.index
plt.figure(figsize=(9.4,9.8))
plt.xticks(np.arange(min(x), max(x)+1, 1.0))
plt.yticks(np.arange(0, 1, step=0.1))  # Set label locations.
plt.scatter(x, y, s=20)

for i, label in enumerate(z):
    plt.annotate(z[i], 
                 (x[i], y[i]),
                 xytext=(8, 0),     # Offset text by 7 points to the right
                 textcoords='offset points', # tell it to use offset points
                 )


plt.show()