KmeansProject

K-Means_Project.py

# importing

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns



df=pd.read_csv("C:\\Users\MageshMacpeth\Desktop\College_Data.csv",index_col = 0)
print(df)

sns.lmplot(data=df,x='Room.Board',y='Grad.Rate',hue='Private',fit_reg=False,palette='coolwarm')
plt.show()

sns.lmplot(data=df,x='Outstate',y='F.Undergrad',hue='Private',fit_reg=False)
plt.show()


o = sns.FacetGrid(df,hue='Private',palette='coolwarm')
o = o.map(plt.hist,'Outstate',bins=20,alpha=0.7)
plt.show()


g = sns.FacetGrid(df,hue='Private',palette='coolwarm')
g = g.map(plt.hist,'Grad.Rate',bins=20,alpha=0.7)
plt.show()


psg=df[df["Grad.Rate"]>100]

df['Grad.Rate']['Cazenovia College']=100
g = sns.FacetGrid(df,hue='Private',palette='coolwarm')
g = g.map(plt.hist,'Grad.Rate',bins=20,alpha=0.7)
plt.show()



from sklearn.cluster import KMeans

kmeans=KMeans(n_clusters=2)
kmeans.fit(df.drop('Private',axis=1))

print(kmeans)