k-NN, Linear Regression, Cross Validation using scikit-learn

In [72]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
import warnings
warnings.filterwarnings('ignore')
%config InlineBackend.figure_format = 'retina'

kNN¶

In [4]:

from sklearn.datasets import load_iris

In [5]:

iris = load_iris()

In [8]:

X = iris.data

In [10]:

y = iris.target

In [11]:

from sklearn.neighbors import KNeighborsClassifier

In [12]:

knn = KNeighborsClassifier(n_neighbors=1)

In [13]:

knn

Out[13]:

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=1, p=2,
           weights='uniform')

In [14]:

knn.fit(X,y)

Out[14]:

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=1, p=2,
           weights='uniform')

In [17]:

knn.predict([[1,2,3,4],[2,2,2,2]])

Out[17]:

array([2, 0])

In [20]:

from sklearn.model_selection import train_test_split

In [56]:

X_Train,X_test,y_train, y_test = train_test_split(X,y,test_size = 0.4, random_state = 4)

In [57]:

knn = KNeighborsClassifier(n_neighbors=1)

In [58]:

knn.fit(X_Train, y_train)

Out[58]:

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=1, p=2,
           weights='uniform')

In [59]:

y_predicted = knn.predict(X_test)

In [60]:

y_predicted

Out[60]:

array([2, 0, 2, 2, 2, 1, 2, 0, 0, 1, 0, 0, 0, 1, 2, 0, 1, 0, 0, 2, 0, 2, 1,
       0, 0, 0, 0, 0, 0, 2, 1, 0, 2, 0, 1, 2, 2, 1, 1, 0, 2, 0, 1, 0, 2, 0,
       0, 1, 1, 2, 0, 1, 2, 2, 1, 1, 0, 1, 1, 1])

In [61]:

from sklearn.metrics import accuracy_score

In [62]:

accuracy_score(y_test,y_predicted)

Out[62]:

0.94999999999999996

In [69]:

k = np.arange(1,25)

In [70]:

k_result = []
for val in k:
    knn = KNeighborsClassifier(n_neighbors=val)
    knn.fit(X_Train,y_train)
    y_predict = knn.predict(X_test)
    k_result.append(accuracy_score(y_test,y_predict))

In [71]:

plt.plot(k,k_result)

Out[71]:

[<matplotlib.lines.Line2D at 0x11b69d710>]

Linear Regression¶

In [73]:

data = pd.read_csv('http://www-bcf.usc.edu/~gareth/ISL/Advertising.csv', index_col=0)
data.head()

Out[73]:

	TV	Radio	Newspaper	Sales
1	230.1	37.8	69.2	22.1
2	44.5	39.3	45.1	10.4
3	17.2	45.9	69.3	9.3
4	151.5	41.3	58.5	18.5
5	180.8	10.8	58.4	12.9

In [77]:

sns.pairplot(data, x_vars=["TV","Radio","Newspaper"], y_vars="Sales", size=7, aspect=0.8)

Out[77]:

<seaborn.axisgrid.PairGrid at 0x11f9c76a0>

In [78]:

sns.pairplot(data, x_vars=["TV","Radio","Newspaper"], y_vars="Sales", size=7, aspect=0.8, kind="reg")

Out[78]:

<seaborn.axisgrid.PairGrid at 0x11fe50c50>

In [79]:

X = data[["TV","Radio","Newspaper"]]

In [80]:

X.head()

Out[80]:

	TV	Radio	Newspaper
1	230.1	37.8	69.2
2	44.5	39.3	45.1
3	17.2	45.9	69.3
4	151.5	41.3	58.5
5	180.8	10.8	58.4

In [81]:

y = data["Sales"]

In [82]:

y.head()

Out[82]:

1    22.1
2    10.4
3     9.3
4    18.5
5    12.9
Name: Sales, dtype: float64

In [84]:

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

In [85]:

X_train, X_test, y_train, y_test = train_test_split(X,y, random_state = 7, test_size = 0.3)

In [86]:

model = LinearRegression()

In [87]:

model.fit(X_train, y_train)

Out[87]:

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)

In [89]:

predicted = model.predict(X_test)

In [91]:

np.sqrt(mean_squared_error(y_test, predicted))

Out[91]:

1.6470911556016581

In [92]:

model.intercept_

Out[92]:

2.5971913990213036

In [93]:

model.coef_

Out[93]:

array([  4.71259657e-02,   1.90987993e-01,  -1.93812266e-05])

kFold Cross Validation¶

In [94]:

data = pd.read_csv('http://www-bcf.usc.edu/~gareth/ISL/Advertising.csv', index_col=0)

In [95]:

X = data[["TV","Radio","Newspaper"]]
y = data["Sales"]

In [96]:

from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score

In [112]:

model = LinearRegression()
kfold = KFold(n_splits=10)
score = cross_val_score(model,X,y,cv = kfold,scoring = "mean_squared_error")

In [113]:

score

Out[113]:

array([-3.56038438, -3.29767522, -2.08943356, -2.82474283, -1.3027754 ,
       -1.74163618, -8.17338214, -2.11409746, -3.04273109, -2.45281793])

In [114]:

score.mean()

Out[114]:

-3.0599676181185136

In [115]:

score = -score.mean()

In [116]:

score = np.sqrt(score)

In [117]:

score

Out[117]:

1.749276312684338