Untitled

from sklearn.model_selection import train_test_split
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.neighbors import KNeighborsClassifier
import  numpy as np
from sklearn.datasets import load_digits
digits = load_digits()
print(digits.DESCR)

digits.target[::100]
digits.data.shape

digits.images[13]
figure, axes= plt.subplots(nrows = 4, ncols = 6, figsize=(6,4))

for item in zip(axes.ravel(), digits.images, digits.target):
  axes, image, target = item
  axes.imshow(image, cmap=plt.cm.gray_r)
  axes.set_xticks([])
  axes.set_yticks([])
  axes.set_title(target)
plt.tight_layout()


from sklearn.datasets import load_digits

digits = load_digits()

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split( digits.data, digits.target, random_state=11)
X_train.shape
X_test.shape

X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target, random_state=11, test_size=0.20)
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier()
knn.fit(X=X_train, y = y_train)

predicted = knn.predict(X = X_test)
expected = y_test

predicted[:20]
expected[:20]

wrong = [(p, e) for (p, e) in zip (predicted, expected) if p != e]
wrong


from sklearn.datasets import load_iris
iris = load_iris()
print(iris.DESCR)
iris.data.shape
iris.target.shape
iris.target_names
iris.feature_names

pd.set_option('max_columns', 5)
pd.set_option('display.width', None)

from sklearn.cluster import KMeans 
kmeans = KMeans(n_clusters= 3 , random_state = 11)
kmeans.fit(iris.data)
print(kmeans.labels_[0:50])

iris_df = pd.DataFrame(iris.data, columns = iris.feature_names)
iris_df['species']= [iris.target_names[i] for i in iris.target]
iris_df.head()
pd.set_option('precision', 2)
iris_df.describe()

import seaborn as sns 
sns.set(font_scale=1.1)
sns.set_style('whitegrid')
grid = sns.pairplot(data = iris_df, vars = iris_df.columns[0:4], hue = 'species')