logestic regression

import pandas as pd
from sklearn import linear_model
import matplotlib.pyplot as plt

In [59]:

df = pd.read_csv("areadata.csv")
df

Out[59]:

	age	bought_insaurance
0	22	0
1	25	0
2	47	1
3	52	0
4	46	1
5	56	0
6	24	0
7	65	1
8	23	0
9	32	1
10	43	1
11	34	1
12	45	0
13	54	1
14	65	0
15	13	0
16	42	1
17	35	0
18	53	1
19	61	0
20	62	0

In [60]:

%matplotlib inline 
plt.xlabel("age")
plt.ylabel("bought_insaurance")
plt.scatter(df.age,df.bought_insaurance,color="red",marker=".")

Out[60]:

<matplotlib.collections.PathCollection at 0x18712cad548>

In [63]:

from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(df[["age"]],df.bought_insaurance,test_size=0.1)

In [66]:

x_test

Out[66]:

	age
1	25
9	32
4	46

In [67]:

x_train

Out[67]:

	age
20	62
12	45
16	42
8	23
18	53
13	54
19	61
7	65
17	35
14	65
2	47
0	22
3	52
6	24
15	13
11	34
5	56
10	43

In [73]:

from sklearn.linear_model import LogisticRegression
model= LogisticRegression()
model.fit(x_train,y_train)

Out[73]:

LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
                   intercept_scaling=1, l1_ratio=None, max_iter=100,
                   multi_class='auto', n_jobs=None, penalty='l2',
                   random_state=None, solver='lbfgs', tol=0.0001, verbose=0,
                   warm_start=False)

In [74]:

x_test

Out[74]:

	age
1	25
9	32
4	46

In [79]:

model.predict_proba([[91]])

Out[79]:

array([[0.29397733, 0.70602267]])

In [ ]: