import codecademylib3_seaborn
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.cluster import KMeans

iris = datasets.load_iris()

samples = iris.data

# Create a model that finds 3 clusters
model = KMeans(n_clusters=3)

# Fit the model to samples
model.fit(samples)

# Determine the labels of samples 
labels = model.predict(samples)

# Print the labels
print(labels)

import codecademylib3_seaborn
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets
from sklearn.cluster import KMeans

iris = datasets.load_iris()

samples = iris.data

model = KMeans(n_clusters=3)

model.fit(samples)

# Store the new Iris measurements
new_samples = np.array([[5.7, 4.4, 1.5, 0.4],
   [6.5, 3. , 5.5, 0.4],
   [5.8, 2.7, 5.1, 1.9]])

# Predict labels for the new_samples
new_labels = model.predict(new_samples)

print(new_labels)

import codecademylib3_seaborn
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.cluster import KMeans

iris = datasets.load_iris()

samples = iris.data

model = KMeans(n_clusters=3)

model.fit(samples)

labels = model.predict(samples)

print(labels)

# Make a scatter plot of x and y and using labels to define the colors
x = samples[:,0]
y = samples[:,1]

plt.scatter(x, y, c=labels, alpha=0.5)

plt.xlabel('sepal length (cm)')
plt.ylabel('sepal width (cm)')

plt.show()

import codecademylib3_seaborn
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn import datasets
from sklearn.cluster import KMeans

iris = datasets.load_iris()

samples = iris.data

# Code Start here:

num_clusters = list(range(1, 9))
inertias = []

for k in num_clusters:
  model = KMeans(n_clusters=k)
  model.fit(samples)
  inertias.append(model.inertia_)
  
plt.plot(num_clusters, inertias, '-o')

plt.xlabel('number of clusters (k)')
plt.ylabel('inertia')

plt.show()