dataset :(https://www.kaggle.com/datasets/mirichoi0218/insurance)

#import libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

#create a dataframe
df=pd.read_csv("insurance.csv")
df.head()

Output:

df.shape

Output: (1338, 7)

df.info()

Output:

df.describe().T

Output:

df['sex']=df['sex'].astype('category')
df['sex']=df['sex'].cat.codes

df.head()

Output:

df['smoker']=df['smoker'].astype('category')
df['smoker']=df['smoker'].cat.codes
df['region']=df['region'].astype('category')
df['region']=df['region'].cat.codes

df.head()

Output:

#Then we will choose X and y
X=df.drop(columns='charges')
X

Output:

y=df['charges']
1338 rows × 6 columns

#split dataset into training and testing data
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_st

print(X_test)

Output:

y_test

Output:

#create linear regression model
from sklearn.linear_model import LinearRegression
model=LinearRegression()

#trained the model
model.fit(X_train,y_train)

Output: LinearRegression()

#predict outcome
y_pred=model.predict(X_test)
y_pred

Output: array([11051.54909755, 9821.28110689, 37867.57220923, 16125.70579228,
 6920.27132517, 3879.38549816, 1448.91928088, 14390.17797974,
 9022.95151353, 7458.83371884, 4584.60125463, 10309.9886336 ,
 8693.03891958, 4085.25393494, 27551.60737718, 11151.0640722 ,
 11243.0536825 , 5962.9521121 , 8181.9015666 , 26750.7993431 ,
 33448.59842228, 14350.03320383, 11672.89478465, 32235.7832204 ,
 4326.07702625, 9096.53607025, 1045.25196369, 10177.76672094,
 4042.60346751, 10384.28681219, 9035.98983755, 40123.71002379,
 15507.20819083, 13678.264976 , 24481.97362849, 5059.21988589,
 12889.80609711, 30333.92625689, 33301.25091403, 3431.35787088,
 3941.81614597, 4203.90901434, 30219.19050725, 39245.56885373,
 27762.83744249, 4994.74188765, 11042.48621304, 7760.15047885,
 3569.09734756, 10613.61535955, 5544.95921408, 3397.80923785,
 32701.67144343, 38285.57836702, 16290.50463759, 6965.99677468,
 5895.27536963, 9364.94083823, 9395.1780384 , 11722.13868077,
 1611.87873326, 38750.4981005 , 15296.11225478, 11708.42958487,
 14076.39653066, 13904.28564489, 25798.46519738, 31953.12169371,
 1168.25915489, 10184.5995492 , 12273.00414884, 11867.15734569,
 24808.10644113, 15908.53043993, 11198.67421883, 12631.50869281,
 6433.71238434, 9915.55343233, 29953.19794316, 38768.07351788,
 12011.54405755, 37253.64166612, 4056.21325429, 9255.50826428,
 34537.73817683, 28976.62623495, 8444.02316285, 4738.69241453,
 11959.22562859, 30006.0695852 , 10041.58386562, 11243.48874027,
 8183.6075869 , 9280.51490529, 8255.40224617, 7239.23538241,
 35731.00350944, 32878.29978853, 7591.7717691 , 14921.91368481,
 4184.53547122, 8690.01064385, 6619.75457992, 31535.59819898,
 32775.00677547, 1887.67848916, 8933.68024017, 6520.27249906,
 14475.77105663, 36880.82790297, 10252.51955517, 10775.16399139,
 10192.95246113, 26581.47470665, 39936.28907748, 8453.03671416,
 143.08142864, 8874.82383918, 15117.85425873, 9557.08594807,
 35275.59070316, 7270.62037452, 16826.50981439, 9572.8088055 ,
 8159.95902395, 2952.65859719, 32706.51413703, 31283.9896012 ,
 39216.89699401, 5362.49911669, 9675.40479836, 3778.85297694,
 7946.39718647, 8585.02883773, 31341.17050506, 29551.7714624 ,
 29853.91861524, 9151.88904567, 32625.66390263, 3229.01239018,
 3529.93652932, 11054.17156002, 13442.38216447, 12761.80223436,
 5363.70249634, 15875.56674406, 15252.72853146, 2382.17016287,
 -120.56014234, 10834.07802124, 7372.12214193, 31759.88622234,
 12314.86913452, 2548.30390645, 6284.28252705, 8170.0107525 ,
 4285.24015268, 2331.14818812, 11414.21888159, 12551.18010753,
 7208.95663304, 16615.95420641, 11792.56220606, 13920.69808423,
 3134.30793579, 7262.13973297, 22758.38813544, 7596.99822972,
 5401.65993492, 5339.75438707, 6641.09944767, 5142.27041 ,
 9983.03913716, 5526.89132472, 5628.18992827, 6975.95618531,
 3673.17907317, 5521.32735633, 37913.25218948, 1337.01243212,
 12636.06438156, 8935.78276524, 13661.56267036, 5572.770716 ,
 5181.38538205, 36214.23931831, 4207.49996636, 1896.75580314,
 15163.16594007, 12674.02182014, 34823.20434979, 5093.20670396,
 5580.90282376, 31320.99694717, 5982.46375195, 1940.59597738,
 8389.18364163, 10016.84576515, 8238.45168712, 5687.97489766,
 13133.993244 , 38538.79843345, 13749.62605459, 28607.07797491,
 6685.39503417, 35610.2777963 , 3716.13611211, 12131.97274228,
 9356.80352592, 6339.94803517, 11268.82158683, 14519.98276598,
 5175.63113265, 4233.99203814, 7768.5658748 , 1150.93881984,
 7861.51707835, 4401.34365822, 13351.6815701 , 4312.6173173 ,
 10007.10646576, 7274.06437597, 9167.81641515, 2307.24223958,
 13115.48905979, 16739.15126554, 15287.81532153, 10516.20091624,
 5706.41694356, 2453.74757235, 2105.41152789, 13376.27751148,
 14339.33209654, 5021.89418573, 4090.605953 , 9366.33184625,
 9969.15202337, 27902.13744062, 7572.78791802, 10543.34735666,
 6174.31283586, 29537.11622517, 11027.94086667, 7457.00641596,
 10225.18823673, 12176.62074648, 2939.88516441, 10785.5019008 ,
 1443.73866643, 6998.45741682, 28534.01786505, 38460.70771961,
 6225.11287288, 8374.92523275, 2386.63715545, 305.52277009,
 10407.09161902, 4362.55365462, 4960.62107139, 2662.94916464,
 7249.10943879, 33132.60876475, 37964.64601751, 14795.4925882 ,
 8191.23299164, 16000.85775643, 33002.87197448, 9520.82908522,
 33323 6218328 3516 92369698 30497 30098573 8044 20793611
 14191.55955407, 4083.10066112, 32268.03153529, 8315.02063095,
 11483.73451116, 9510.21374527, 4115.91551624, 12660.02379304,
 11717.00935707, 8354.17363399, 13269.77614371, 2699.20978031,
 10542.22785417, 5391.53803822, 11313.67089224, 31398.88972707,
 10029.81495966, 1118.21159472, 462.52270438, 39674.38015203,
 9676.2207617 , 7081.42950834, 13999.68415448, 13421.82776838,
 26976.22819473, 7100.7475948 , 6788.44279001, 12033.45246932,
 2786.36526883, 3902.46962572, 24859.29396183, 26090.84463032,
 13371.81813565, 3164.31052787, 5117.58945791, 9325.3139586 ,
 12404.934023 , 23317.59720695, 30625.80462982, 10046.65063794,
 23804.49406862, 2804.50033014, 11550.33636023, 7549.77464787,
 8233.25736365, 312.94242569, 7720.18671702, 35401.11202663,
 6152.78016128, 6237.66443531, 178.89028134, 10901.70768044,
 6750.59209883, 9992.98880624, 38764.63808826, 27466.58793525,
 11489.14198588, 35484.16547957, 15039.21254017, 6810.42408411,
 11015.353549 , 6839.24282704, 36512.17018034, 6045.00741789,
 11075.16473053, 741.96608741, 24186.22593789, 1881.15932715,
 34245.135946 , 11379.34404185, 1787.47141685, 32018.68078654,
 6644.72832713, 5200.52497017, 37952.77965645, 2171.21921984,
 9595.04338665, 2650.53107838, 12806.89011534, 1008.0849294 ,
 11113.81326429, 7092.09772183, 36343.11043514, 7160.77113975,
 30438.75625726, 29472.1875026 , 7100.76722883, 10790.23315907,
 1879.90465675, 2200.37960027, 3793.92758918, 12706.65566117,
 37039.77367021, 9716.69560709, 345.17579449, 11387.82123255,
 5036.80429065, 9779.98465515, 5576.16518582, 7260.90814745,
 4311.38104385, 28280.88564325, 4363.51594298, -921.56882455,
 33139.88333244, 12910.28546987, 35733.85862246, 9841.66334273,
 7663.70159627, -94.4834943 , 2560.96139226, 11527.50523772,
 5669.76181684, 3293.09776754, 12120.72252044, 7743.17735694,
 6920.9128887 , 5459.93977214, 3049.37781558, 31786.79912085,
 3518.32063003, 8595.19234733, 4796.86509127, 13024.5060374 ,
 14691.59701387, 7163.95913996, 26454.5855911 , 14277.02407734,
 17354.84539043, 11476.70520069])

from sklearn.metrics import r2_score
r2_score(y_test,y_pred)

Output: 0.7911113876316933

plt.scatter(y_test,y_pred)
plt.xlabel('Actual charges')
plt.ylabel('predicted charges')
plt.show()