Lesson 2 - Matplot Library.ipynb

Kernel: Python 3 (system-wide)

import numpy as np

import pandas as pd

from matplotlib import pyplot as plt

from sklearn.datasets.samples_generator import make_blobs

/usr/local/lib/python3.6/dist-packages/sklearn/utils/deprecation.py:143: FutureWarning: The sklearn.datasets.samples_generator module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.datasets. Anything that cannot be imported from sklearn.datasets is now part of the private API.
  warnings.warn(message, FutureWarning)

from sklearn.cluster import KMeans

X, y = make_blobs(n_samples=300, centers=4, cluster_std=0.60, random_state=0)

plt.scatter(X[:,0], X[:,1])

<matplotlib.collections.PathCollection at 0x7f43a8a6b8d0>

wcss = []

for i in range(1, 11):
    kmeans = KMeans(n_clusters=i, init='k-means++', max_iter=300, n_init=10, random_state=0)
    kmeans.fit(X)
    wcss.append(kmeans.inertia_)

plt.plot(range(1, 11), wcss)
plt.title('Elbow Method')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()

kmeans = KMeans(n_clusters=4, init='k-means++', max_iter=300, n_init=10, random_state=0)
pred_y = kmeans.fit_predict(X)
plt.scatter(X[:,0], X[:,1])
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=300, c='red')
plt.show()

import pandas as pd

from matplotlib import pyplot as plt

import sklearn

from sklearn import datasets

from sklearn.cluster import KMeans

from mpl_toolkits.mplot3d import Axes3D

from sklearn.preprocessing import scale

import sklearn.metrics as sm

iris = datasets.load_iris()
#https://scikit-learn.org/stable/modules/classes.html#module-sklearn.datasets for other data sets.

X = scale(iris.data)

y = pd.DataFrame(iris.target)

variable_names = iris.feature_names

X[0:10,]

array([[-0.90068117,  1.01900435, -1.34022653, -1.3154443 ],
       [-1.14301691, -0.13197948, -1.34022653, -1.3154443 ],
       [-1.38535265,  0.32841405, -1.39706395, -1.3154443 ],
       [-1.50652052,  0.09821729, -1.2833891 , -1.3154443 ],
       [-1.02184904,  1.24920112, -1.34022653, -1.3154443 ],
       [-0.53717756,  1.93979142, -1.16971425, -1.05217993],
       [-1.50652052,  0.78880759, -1.34022653, -1.18381211],
       [-1.02184904,  0.78880759, -1.2833891 , -1.3154443 ],
       [-1.74885626, -0.36217625, -1.34022653, -1.3154443 ],
       [-1.14301691,  0.09821729, -1.2833891 , -1.44707648]])

clustering = KMeans(n_clusters = 3, random_state = 5)

clustering.fit(X)

KMeans(n_clusters=3, random_state=5)

iris_df = pd.DataFrame(iris.data)

iris_df.shape

(150, 4)

iris_df.head()

	0	1	2	3
0	5.1	3.5	1.4	0.2
1	4.9	3.0	1.4	0.2
2	4.7	3.2	1.3	0.2
3	4.6	3.1	1.5	0.2
4	5.0	3.6	1.4	0.2

iris_df.columns = ["Sepal_Length","Sepal_Width","Petal_Length","Petal_Width"]

y.columns = ["Target"]

iris_df.head()

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width
0	5.1	3.5	1.4	0.2
1	4.9	3.0	1.4	0.2
2	4.7	3.2	1.3	0.2
3	4.6	3.1	1.5	0.2
4	5.0	3.6	1.4	0.2

color_theme = np.array(['darkgray','lightsalmon','powderblue'])

plt.subplot(1,2,1)

<AxesSubplot:>

plt.scatter(x=iris_df.Petal_Length, y =iris_df.Petal_Width, c=color_)