3/23/2019 Advertising
In [2]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
In [3]:
import seaborn as sns
sns.set_style('darkgrid')
In [4]:
%matplotlib inline
In [6]:
file = r'C:\Users\hp\Desktop\advertising.csv'
data = pd.read_csv(file)
In [7]:
data.head()
Out[7]:
Unnamed: 0 TV radio newspaper sales
0 1 230.1 37.8 69.2 22.1
1 2 44.5 39.3 45.1 10.4
2 3 17.2 45.9 69.3 9.3
3 4 151.5 41.3 58.5 18.5
4 5 180.8 10.8 58.4 12.9
In [20]:
data.drop(['Unnamed: 0'],axis = 1,inplace = True)
In [11]:
data.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 200 entries, 0 to 199
Data columns (total 5 columns):
Unnamed: 0 200 non-null int64
TV 200 non-null float64
radio 200 non-null float64
newspaper 200 non-null float64
sales 200 non-null float64
dtypes: float64(4), int64(1)
memory usage: 7.9 KB
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 1/12
3/23/2019 Advertising
In [21]:
data.describe()
Out[21]:
TV radio newspaper sales
count 200.000000 200.000000 200.000000 200.000000
mean 147.042500 23.264000 30.554000 14.022500
std 85.854236 14.846809 21.778621 5.217457
min 0.700000 0.000000 0.300000 1.600000
25% 74.375000 9.975000 12.750000 10.375000
50% 149.750000 22.900000 25.750000 12.900000
75% 218.825000 36.525000 45.100000 17.400000
max 296.400000 49.600000 114.000000 27.000000
In [22]:
sns.heatmap(data.corr(),cmap = 'magma',lw = .7,linecolor = 'black',alpha = 0.8,annot =
True)
Out[22]:
<matplotlib.axes._subplots.AxesSubplot at 0x1ed5ba54630>
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 2/12
3/23/2019 Advertising
In [30]:
sns.distplot(data['sales'],hist = True)
Out[30]:
<matplotlib.axes._subplots.AxesSubplot at 0x1ed5bf0be10>
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 3/12
3/23/2019 Advertising
In [29]:
sns.lmplot(x = 'TV',y = 'radio',data = data)
Out[29]:
<seaborn.axisgrid.FacetGrid at 0x1ed5beaa7f0>
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 4/12
3/23/2019 Advertising
In [35]:
sns.pairplot(data)
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 5/12
3/23/2019 Advertising
Out[35]:
<seaborn.axisgrid.PairGrid at 0x1ed5f436978>
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 6/12
3/23/2019 Advertising
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 7/12
3/23/2019 Advertising
In [36]:
data.head()
Out[36]:
TV radio newspaper sales
0 230.1 37.8 69.2 22.1
1 44.5 39.3 45.1 10.4
2 17.2 45.9 69.3 9.3
3 151.5 41.3 58.5 18.5
4 180.8 10.8 58.4 12.9
In [39]:
X = data.drop(['sales'],axis = 1)
y = data['sales']
In [40]:
from sklearn.model_selection import train_test_split
In [41]:
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1
01)
In [42]:
from sklearn.linear_model import LogisticRegression
In [44]:
logmodel = LogisticRegression()
In [56]:
from sklearn import preprocessing
from sklearn import utils
lab_enc = preprocessing.LabelEncoder()
encoded = lab_enc.fit_transform(y_train)
In [66]:
lab_enc = preprocessing.LabelEncoder()
encoded2 = lab_enc.fit_transform(y_test)
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 8/12
3/23/2019 Advertising
In [60]:
logmodel.fit(X_train,encoded)
C:\Users\hp\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:4
33: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Spec
ify a solver to silence this warning.
FutureWarning)
C:\Users\hp\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:4
60: FutureWarning: Default multi_class will be changed to 'auto' in 0.22.
Specify the multi_class option to silence this warning.
"this warning.", FutureWarning)
Out[60]:
LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=Tru
e,
intercept_scaling=1, max_iter=100, multi_class='warn',
n_jobs=None, penalty='l2', random_state=None, solver='warn',
tol=0.0001, verbose=0, warm_start=False)
In [61]:
predictions = logmodel.predict(X_test)
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 9/12
3/23/2019 Advertising
In [69]:
from sklearn.metrics import classification_report,confusion_matrix
print(classification_report(encoded2,predictions))
print(confusion_matrix)
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 10/12
3/23/2019 Advertising
precision recall f1-score support
0 0.00 0.00 0.00 1
1 0.00 0.00 0.00 1
2 0.00 0.00 0.00 1
3 0.00 0.00 0.00 1
4 0.00 0.00 0.00 1
5 0.00 0.00 0.00 1
6 0.00 0.00 0.00 1
7 0.00 0.00 0.00 1
8 0.00 0.00 0.00 1
9 0.50 0.50 0.50 2
10 0.00 0.00 0.00 2
11 0.00 0.00 0.00 1
12 0.00 0.00 0.00 2
13 0.00 0.00 0.00 1
14 0.00 0.00 0.00 2
15 0.00 0.00 0.00 1
16 0.00 0.00 0.00 1
17 0.00 0.00 0.00 2
18 0.00 0.00 0.00 1
19 0.00 0.00 0.00 1
20 0.00 0.00 0.00 1
21 0.00 0.00 0.00 1
22 0.00 0.00 0.00 2
23 0.00 0.00 0.00 1
24 0.00 0.00 0.00 1
25 0.00 0.00 0.00 2
26 0.00 0.00 0.00 1
27 0.00 0.00 0.00 1
28 0.00 0.00 0.00 1
29 0.00 0.00 0.00 2
30 0.00 0.00 0.00 1
31 0.00 0.00 0.00 1
32 0.00 0.00 0.00 2
33 0.00 0.00 0.00 1
34 0.00 0.00 0.00 1
35 0.00 0.00 0.00 1
36 0.00 0.00 0.00 1
37 0.00 0.00 0.00 1
38 0.00 0.00 0.00 1
39 0.00 0.00 0.00 1
40 0.00 0.00 0.00 1
41 0.00 0.00 0.00 1
42 0.00 0.00 0.00 1
43 0.00 0.00 0.00 1
44 0.00 0.00 0.00 1
45 0.00 0.00 0.00 1
46 0.00 0.00 0.00 1
47 0.00 0.00 0.00 1
48 0.00 0.00 0.00 1
49 0.00 0.00 0.00 1
50 0.00 0.00 0.00 1
54 0.00 0.00 0.00 0
63 0.00 0.00 0.00 0
73 0.00 0.00 0.00 0
81 0.00 0.00 0.00 0
84 0.00 0.00 0.00 0
95 0.00 0.00 0.00 0
98 0.00 0.00 0.00 0
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 11/12
3/23/2019 Advertising
micro avg 0.02 0.02 0.02 60
macro avg 0.01 0.01 0.01 60
weighted avg 0.02 0.02 0.02 60
<function confusion_matrix at 0x000001ED6141F7B8>
C:\Users\hp\Anaconda3\lib\site-packages\sklearn\metrics\classification.py:
1143: UndefinedMetricWarning: Precision and F-score are ill-defined and be
ing set to 0.0 in labels with no predicted samples.
'precision', 'predicted', average, warn_for)
C:\Users\hp\Anaconda3\lib\site-packages\sklearn\metrics\classification.py:
1145: UndefinedMetricWarning: Recall and F-score are ill-defined and being
set to 0.0 in labels with no true samples.
'recall', 'true', average, warn_for)
C:\Users\hp\Anaconda3\lib\site-packages\sklearn\metrics\classification.py:
1143: UndefinedMetricWarning: Precision and F-score are ill-defined and be
ing set to 0.0 in labels with no predicted samples.
'precision', 'predicted', average, warn_for)
C:\Users\hp\Anaconda3\lib\site-packages\sklearn\metrics\classification.py:
1145: UndefinedMetricWarning: Recall and F-score are ill-defined and being
set to 0.0 in labels with no true samples.
'recall', 'true', average, warn_for)
C:\Users\hp\Anaconda3\lib\site-packages\sklearn\metrics\classification.py:
1143: UndefinedMetricWarning: Precision and F-score are ill-defined and be
ing set to 0.0 in labels with no predicted samples.
'precision', 'predicted', average, warn_for)
C:\Users\hp\Anaconda3\lib\site-packages\sklearn\metrics\classification.py:
1145: UndefinedMetricWarning: Recall and F-score are ill-defined and being
set to 0.0 in labels with no true samples.
'recall', 'true', average, warn_for)
In [ ]:
http://localhost:8888/nbconvert/html/Advertising.ipynb?download=false 12/12
