whitehatjr/c125

solution for C125

c125's Issues

Solution for class 118 Pro.ipynb

from google.colab import files
data_to_load = files.upload()

import pandas as pd
import plotly.express as px

df = pd.read_csv("stars.csv")
print(df.head())

from sklearn.cluster import KMeans
X = df.iloc[:, [0, 1]].values
print( X)

wcss = []
for i in range(1, 11):
kmeans = KMeans(n_clusters=i, init='k-means++', random_state = 42)
kmeans.fit(X)
wcss.append(kmeans.inertia_)

import matplotlib.pyplot as plt
import seaborn as sns

plt.figure(figsize = (10,5))
sns.lineplot(range(1,11),wcss,marker= "o",color = "red")
plt.title("the_elbow_method")
plt.xlabel("number of clusters")
plt.ylabel("wcss")
plt.show()

plt.figure(figsize = (15,7))
sns.scatterplot(X[y_kmeans == 0,0],X[y_kmeans == 0,1],color = "purple",label = "cluster1")
sns.scatterplot(X[y_kmeans == 1,0],X[y_kmeans == 1,1],color = "orange",label = "cluster2")
sns.scatterplot(X[y_kmeans == 2,0],X[y_kmeans == 2,1],color = "pink",label = "cluster3")

sns.scatterplot(kmeans.cluster_centers_[:,0],kmeans.cluster_centers_[:,1],color = "red",label = "centroid",s = 100,markers=",")
plt.grid(False)
plt.title("cluster of stars")
plt.xlabel("stars")
plt.ylabel("light")
plt.legend()
plt.show()