
import warnings
warnings.filterwarnings('ignore')

#importing the libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from word2number import w2n
from tqdm import tqdm


!pip install word2number

Requirement already satisfied: word2number in c:\users\ghoshs\appdata\local\continuum\anaconda3\lib\site-packages (1.1)


cars = pd.read_csv('CarPrice_Assignment.csv')


cars.head(2)


cars.tail()


cars.shape

(205, 26)


cars.describe()


cars.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 205 entries, 0 to 204
Data columns (total 26 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   car_ID            205 non-null    int64  
 1   symboling         205 non-null    int64  
 2   CarName           205 non-null    object 
 3   fueltype          194 non-null    object 
 4   aspiration        205 non-null    object 
 5   doornumber        205 non-null    object 
 6   carbody           200 non-null    object 
 7   drivewheel        205 non-null    object 
 8   enginelocation    193 non-null    object 
 9   wheelbase         205 non-null    float64
 10  carlength         205 non-null    float64
 11  carwidth          205 non-null    float64
 12  carheight         205 non-null    float64
 13  curbweight        205 non-null    int64  
 14  enginetype        205 non-null    object 
 15  cylindernumber    205 non-null    object 
 16  enginesize        205 non-null    int64  
 17  fuelsystem        205 non-null    object 
 18  boreratio         205 non-null    float64
 19  stroke            205 non-null    float64
 20  compressionratio  205 non-null    float64
 21  horsepower        205 non-null    int64  
 22  peakrpm           205 non-null    int64  
 23  citympg           205 non-null    int64  
 24  highwaympg        205 non-null    int64  
 25  price             205 non-null    float64
dtypes: float64(8), int64(8), object(10)
memory usage: 41.8+ KB


cars.columns

Index(['car_ID', 'symboling', 'CarName', 'fueltype', 'aspiration',
       'doornumber', 'carbody', 'drivewheel', 'enginelocation', 'wheelbase',
       'carlength', 'carwidth', 'carheight', 'curbweight', 'enginetype',
       'cylindernumber', 'enginesize', 'fuelsystem', 'boreratio', 'stroke',
       'compressionratio', 'horsepower', 'peakrpm', 'citympg', 'highwaympg',
       'price'],
      dtype='object')


list(cars.columns)

['car_ID',
 'symboling',
 'CarName',
 'fueltype',
 'aspiration',
 'doornumber',
 'carbody',
 'drivewheel',
 'enginelocation',
 'wheelbase',
 'carlength',
 'carwidth',
 'carheight',
 'curbweight',
 'enginetype',
 'cylindernumber',
 'enginesize',
 'fuelsystem',
 'boreratio',
 'stroke',
 'compressionratio',
 'horsepower',
 'peakrpm',
 'citympg',
 'highwaympg',
 'price']


for x in cars.columns:
    print(x)

car_ID
symboling
CarName
fueltype
aspiration
doornumber
carbody
drivewheel
enginelocation
wheelbase
carlength
carwidth
carheight
curbweight
enginetype
cylindernumber
enginesize
fuelsystem
boreratio
stroke
compressionratio
horsepower
peakrpm
citympg
highwaympg
price


cars.describe().T


cars.describe(include='object').T


list(cars.columns[cars.dtypes == 'int64'])

['car_ID',
 'symboling',
 'curbweight',
 'enginesize',
 'horsepower',
 'peakrpm',
 'citympg',
 'highwaympg']


cars.iloc[0:5, 0:4]


cars.loc[0:5,['CarName','fueltype']]


cars['fueltype'].unique()

array(['gas', nan, 'diesel'], dtype=object)


cars['fueltype'].dtype

dtype('O')


cars['fueltype'].value_counts()

gas       174
diesel     20
Name: fueltype, dtype: int64


cars.isnull().sum()

car_ID               0
symboling            0
CarName              0
fueltype            11
aspiration           0
doornumber           0
carbody              5
drivewheel           0
enginelocation      12
wheelbase            0
carlength            0
carwidth             0
carheight            0
curbweight           0
enginetype           0
cylindernumber       0
enginesize           0
fuelsystem           0
boreratio            0
stroke               0
compressionratio     0
horsepower           0
peakrpm              0
citympg              0
highwaympg           0
price                0
dtype: int64


cars.isnull().any()

car_ID              False
symboling           False
CarName             False
fueltype             True
aspiration          False
doornumber          False
carbody              True
drivewheel          False
enginelocation       True
wheelbase           False
carlength           False
carwidth            False
carheight           False
curbweight          False
enginetype          False
cylindernumber      False
enginesize          False
fuelsystem          False
boreratio           False
stroke              False
compressionratio    False
horsepower          False
peakrpm             False
citympg             False
highwaympg          False
price               False
dtype: bool


cars_copy = cars.copy()


null_columns=cars.columns[cars.isnull().any()]
cars[null_columns].isnull().sum()*100/len(cars)

fueltype          5.365854
carbody           2.439024
enginelocation    5.853659
dtype: float64


list(null_columns)

['fueltype', 'carbody', 'enginelocation']


for x in cars.columns[cars.isnull().any()]:
    print('--------------------------------')
    print('Column Name:',x)
    print('--------------------------------')
    print(cars[x].value_counts()*100/len(cars))
    print(cars[x].value_counts())

--------------------------------
Column Name: fueltype
--------------------------------
gas       84.878049
diesel     9.756098
Name: fueltype, dtype: float64
gas       174
diesel     20
Name: fueltype, dtype: int64
--------------------------------
Column Name: carbody
--------------------------------
sedan          44.390244
hatchback      34.146341
wagon          12.195122
hardtop         3.902439
convertible     2.926829
Name: carbody, dtype: float64
sedan          91
hatchback      70
wagon          25
hardtop         8
convertible     6
Name: carbody, dtype: int64
--------------------------------
Column Name: enginelocation
--------------------------------
front    92.682927
rear      1.463415
Name: enginelocation, dtype: float64
front    190
rear       3
Name: enginelocation, dtype: int64


cars['fueltype'].fillna (value='gas', inplace = True)
cars['enginelocation'].fillna (value='front', inplace = True)


cars['fueltype'].unique()

array(['gas', 'diesel'], dtype=object)


cars['enginelocation'].unique()

array(['front', 'rear'], dtype=object)


for x in cars.columns:
    print('--------------------------------')
    print('Column Name:',x)
    print('--------------------------------')
    print(cars[x].value_counts()*100/len(cars))
    print(cars[x].value_counts())

--------------------------------
Column Name: car_ID
--------------------------------
1      0.487805
142    0.487805
132    0.487805
133    0.487805
134    0.487805
         ...   
72     0.487805
73     0.487805
74     0.487805
75     0.487805
205    0.487805
Name: car_ID, Length: 205, dtype: float64
1      1
142    1
132    1
133    1
134    1
      ..
72     1
73     1
74     1
75     1
205    1
Name: car_ID, Length: 205, dtype: int64
--------------------------------
Column Name: symboling
--------------------------------
 0    32.682927
 1    26.341463
 2    15.609756
 3    13.170732
-1    10.731707
-2     1.463415
Name: symboling, dtype: float64
 0    67
 1    54
 2    32
 3    27
-1    22
-2     3
Name: symboling, dtype: int64
--------------------------------
Column Name: CarName
--------------------------------
toyota corona           2.926829
toyota corolla          2.926829
peugeot 504             2.926829
subaru dl               1.951220
mitsubishi mirage g4    1.463415
                          ...   
mazda glc 4             0.487805
mazda rx2 coupe         0.487805
maxda glc deluxe        0.487805
maxda rx3               0.487805
volvo 246               0.487805
Name: CarName, Length: 147, dtype: float64
toyota corona           6
toyota corolla          6
peugeot 504             6
subaru dl               4
mitsubishi mirage g4    3
                       ..
mazda glc 4             1
mazda rx2 coupe         1
maxda glc deluxe        1
maxda rx3               1
volvo 246               1
Name: CarName, Length: 147, dtype: int64
--------------------------------
Column Name: fueltype
--------------------------------
gas       90.243902
diesel     9.756098
Name: fueltype, dtype: float64
gas       185
diesel     20
Name: fueltype, dtype: int64
--------------------------------
Column Name: aspiration
--------------------------------
std      81.95122
turbo    18.04878
Name: aspiration, dtype: float64
std      168
turbo     37
Name: aspiration, dtype: int64
--------------------------------
Column Name: doornumber
--------------------------------
four    56.097561
two     43.902439
Name: doornumber, dtype: float64
four    115
two      90
Name: doornumber, dtype: int64
--------------------------------
Column Name: carbody
--------------------------------
sedan          44.390244
hatchback      34.146341
wagon          12.195122
hardtop         3.902439
convertible     2.926829
Name: carbody, dtype: float64
sedan          91
hatchback      70
wagon          25
hardtop         8
convertible     6
Name: carbody, dtype: int64
--------------------------------
Column Name: drivewheel
--------------------------------
fwd    58.536585
rwd    37.073171
4wd     4.390244
Name: drivewheel, dtype: float64
fwd    120
rwd     76
4wd      9
Name: drivewheel, dtype: int64
--------------------------------
Column Name: enginelocation
--------------------------------
front    98.536585
rear      1.463415
Name: enginelocation, dtype: float64
front    202
rear       3
Name: enginelocation, dtype: int64
--------------------------------
Column Name: wheelbase
--------------------------------
94.5     10.243902
93.7      9.756098
95.7      6.341463
96.5      3.902439
97.3      3.414634
98.4      3.414634
104.3     2.926829
100.4     2.926829
107.9     2.926829
98.8      2.926829
99.1      2.926829
96.3      2.926829
109.1     2.439024
93.1      2.439024
97.2      2.439024
95.9      2.439024
102.4     2.439024
97.0      1.951220
95.3      1.951220
114.2     1.951220
101.2     1.951220
110.0     1.463415
103.5     1.463415
89.5      1.463415
105.8     1.463415
96.1      0.975610
102.9     0.975610
104.5     0.975610
91.3      0.975610
96.9      0.975610
88.6      0.975610
113.0     0.975610
99.8      0.975610
115.6     0.975610
103.3     0.975610
86.6      0.975610
104.9     0.975610
93.3      0.487805
99.4      0.487805
99.5      0.487805
88.4      0.487805
94.3      0.487805
96.0      0.487805
95.1      0.487805
93.0      0.487805
102.0     0.487805
106.7     0.487805
108.0     0.487805
96.6      0.487805
99.2      0.487805
112.0     0.487805
102.7     0.487805
120.9     0.487805
Name: wheelbase, dtype: float64
94.5     21
93.7     20
95.7     13
96.5      8
97.3      7
98.4      7
104.3     6
100.4     6
107.9     6
98.8      6
99.1      6
96.3      6
109.1     5
93.1      5
97.2      5
95.9      5
102.4     5
97.0      4
95.3      4
114.2     4
101.2     4
110.0     3
103.5     3
89.5      3
105.8     3
96.1      2
102.9     2
104.5     2
91.3      2
96.9      2
88.6      2
113.0     2
99.8      2
115.6     2
103.3     2
86.6      2
104.9     2
93.3      1
99.4      1
99.5      1
88.4      1
94.3      1
96.0      1
95.1      1
93.0      1
102.0     1
106.7     1
108.0     1
96.6      1
99.2      1
112.0     1
102.7     1
120.9     1
Name: wheelbase, dtype: int64
--------------------------------
Column Name: carlength
--------------------------------
157.3    7.317073
188.8    5.365854
171.7    3.414634
186.7    3.414634
166.3    3.414634
           ...   
165.6    0.487805
187.5    0.487805
180.3    0.487805
208.1    0.487805
199.2    0.487805
Name: carlength, Length: 75, dtype: float64
157.3    15
188.8    11
171.7     7
186.7     7
166.3     7
         ..
165.6     1
187.5     1
180.3     1
208.1     1
199.2     1
Name: carlength, Length: 75, dtype: int64
--------------------------------
Column Name: carwidth
--------------------------------
63.8    11.707317
66.5    11.219512
65.4     7.317073
63.6     5.365854
64.4     4.878049
68.4     4.878049
64.0     4.390244
65.5     3.902439
65.2     3.414634
64.2     2.926829
66.3     2.926829
65.6     2.926829
67.2     2.926829
67.9     2.439024
66.9     2.439024
65.7     1.951220
68.9     1.951220
64.8     1.951220
63.9     1.463415
70.3     1.463415
71.7     1.463415
71.4     1.463415
65.0     1.463415
68.3     0.975610
67.7     0.975610
64.1     0.975610
66.1     0.975610
69.6     0.975610
64.6     0.975610
72.0     0.487805
68.0     0.487805
70.5     0.487805
61.8     0.487805
66.0     0.487805
62.5     0.487805
70.6     0.487805
72.3     0.487805
66.6     0.487805
63.4     0.487805
60.3     0.487805
70.9     0.487805
66.4     0.487805
66.2     0.487805
68.8     0.487805
Name: carwidth, dtype: float64
63.8    24
66.5    23
65.4    15
63.6    11
64.4    10
68.4    10
64.0     9
65.5     8
65.2     7
64.2     6
66.3     6
65.6     6
67.2     6
67.9     5
66.9     5
65.7     4
68.9     4
64.8     4
63.9     3
70.3     3
71.7     3
71.4     3
65.0     3
68.3     2
67.7     2
64.1     2
66.1     2
69.6     2
64.6     2
72.0     1
68.0     1
70.5     1
61.8     1
66.0     1
62.5     1
70.6     1
72.3     1
66.6     1
63.4     1
60.3     1
70.9     1
66.4     1
66.2     1
68.8     1
Name: carwidth, dtype: int64
--------------------------------
Column Name: carheight
--------------------------------
50.8    6.829268
52.0    5.853659
55.7    5.853659
54.1    4.878049
54.5    4.878049
55.5    4.390244
56.7    3.902439
54.3    3.902439
52.6    3.414634
56.1    3.414634
51.6    3.414634
53.0    2.926829
52.8    2.926829
54.9    2.926829
50.2    2.926829
53.7    2.439024
55.1    2.439024
50.6    2.439024
49.6    1.951220
58.7    1.951220
53.3    1.951220
52.5    1.463415
59.1    1.463415
56.2    1.463415
49.7    1.463415
57.5    1.463415
53.5    1.463415
54.4    0.975610
53.9    0.975610
56.3    0.975610
50.5    0.975610
59.8    0.975610
56.5    0.975610
54.7    0.975610
48.8    0.975610
49.4    0.975610
51.4    0.975610
51.0    0.487805
54.8    0.487805
55.4    0.487805
56.0    0.487805
55.2    0.487805
53.2    0.487805
47.8    0.487805
55.9    0.487805
52.4    0.487805
55.6    0.487805
53.1    0.487805
58.3    0.487805
Name: carheight, dtype: float64
50.8    14
52.0    12
55.7    12
54.1    10
54.5    10
55.5     9
56.7     8
54.3     8
52.6     7
56.1     7
51.6     7
53.0     6
52.8     6
54.9     6
50.2     6
53.7     5
55.1     5
50.6     5
49.6     4
58.7     4
53.3     4
52.5     3
59.1     3
56.2     3
49.7     3
57.5     3
53.5     3
54.4     2
53.9     2
56.3     2
50.5     2
59.8     2
56.5     2
54.7     2
48.8     2
49.4     2
51.4     2
51.0     1
54.8     1
55.4     1
56.0     1
55.2     1
53.2     1
47.8     1
55.9     1
52.4     1
55.6     1
53.1     1
58.3     1
Name: carheight, dtype: int64
--------------------------------
Column Name: curbweight
--------------------------------
2385    1.951220
1918    1.463415
2275    1.463415
1989    1.463415
2410    0.975610
          ...   
2370    0.487805
2328    0.487805
2833    0.487805
2921    0.487805
3062    0.487805
Name: curbweight, Length: 171, dtype: float64
2385    4
1918    3
2275    3
1989    3
2410    2
       ..
2370    1
2328    1
2833    1
2921    1
3062    1
Name: curbweight, Length: 171, dtype: int64
--------------------------------
Column Name: enginetype
--------------------------------
ohc      72.195122
ohcf      7.317073
ohcv      6.341463
dohc      5.853659
l         5.853659
rotor     1.951220
dohcv     0.487805
Name: enginetype, dtype: float64
ohc      148
ohcf      15
ohcv      13
dohc      12
l         12
rotor      4
dohcv      1
Name: enginetype, dtype: int64
--------------------------------
Column Name: cylindernumber
--------------------------------
four      77.560976
six       11.707317
five       5.365854
eight      2.439024
two        1.951220
three      0.487805
twelve     0.487805
Name: cylindernumber, dtype: float64
four      159
six        24
five       11
eight       5
two         4
three       1
twelve      1
Name: cylindernumber, dtype: int64
--------------------------------
Column Name: enginesize
--------------------------------
122    7.317073
92     7.317073
97     6.829268
98     6.829268
108    6.341463
90     5.853659
110    5.853659
109    3.902439
120    3.414634
141    3.414634
152    2.926829
181    2.926829
146    2.926829
121    2.926829
156    2.439024
136    2.439024
91     2.439024
183    1.951220
130    1.951220
171    1.463415
70     1.463415
194    1.463415
209    1.463415
164    1.463415
258    0.975610
140    0.975610
134    0.975610
234    0.975610
132    0.975610
131    0.975610
173    0.487805
203    0.487805
161    0.487805
80     0.487805
151    0.487805
103    0.487805
304    0.487805
308    0.487805
326    0.487805
119    0.487805
111    0.487805
79     0.487805
61     0.487805
145    0.487805
Name: enginesize, dtype: float64
122    15
92     15
97     14
98     14
108    13
90     12
110    12
109     8
120     7
141     7
152     6
181     6
146     6
121     6
156     5
136     5
91      5
183     4
130     4
171     3
70      3
194     3
209     3
164     3
258     2
140     2
134     2
234     2
132     2
131     2
173     1
203     1
161     1
80      1
151     1
103     1
304     1
308     1
326     1
119     1
111     1
79      1
61      1
145     1
Name: enginesize, dtype: int64
--------------------------------
Column Name: fuelsystem
--------------------------------
mpfi    45.853659
2bbl    32.195122
idi      9.756098
1bbl     5.365854
spdi     4.390244
4bbl     1.463415
mfi      0.487805
spfi     0.487805
Name: fuelsystem, dtype: float64
mpfi    94
2bbl    66
idi     20
1bbl    11
spdi     9
4bbl     3
mfi      1
spfi     1
Name: fuelsystem, dtype: int64
--------------------------------
Column Name: boreratio
--------------------------------
3.62    11.219512
3.19     9.756098
3.15     7.317073
3.03     5.853659
2.97     5.853659
3.46     4.390244
3.31     3.902439
3.43     3.902439
3.78     3.902439
3.27     3.414634
2.91     3.414634
3.58     2.926829
3.39     2.926829
3.33     2.926829
3.05     2.926829
3.54     2.926829
3.70     2.439024
3.01     2.439024
3.35     1.951220
3.17     1.463415
3.59     1.463415
3.74     1.463415
3.47     0.975610
3.94     0.975610
3.24     0.975610
3.63     0.975610
3.13     0.975610
3.80     0.975610
3.50     0.975610
2.54     0.487805
3.08     0.487805
3.61     0.487805
3.34     0.487805
2.68     0.487805
3.60     0.487805
2.92     0.487805
3.76     0.487805
2.99     0.487805
Name: boreratio, dtype: float64
3.62    23
3.19    20
3.15    15
3.03    12
2.97    12
3.46     9
3.31     8
3.43     8
3.78     8
3.27     7
2.91     7
3.58     6
3.39     6
3.33     6
3.05     6
3.54     6
3.70     5
3.01     5
3.35     4
3.17     3
3.59     3
3.74     3
3.47     2
3.94     2
3.24     2
3.63     2
3.13     2
3.80     2
3.50     2
2.54     1
3.08     1
3.61     1
3.34     1
2.68     1
3.60     1
2.92     1
3.76     1
2.99     1
Name: boreratio, dtype: int64
--------------------------------
Column Name: stroke
--------------------------------
3.400    9.756098
3.230    6.829268
3.150    6.829268
3.030    6.829268
3.390    6.341463
2.640    5.365854
3.290    4.390244
3.350    4.390244
3.460    3.902439
3.110    2.926829
3.270    2.926829
3.410    2.926829
3.070    2.926829
3.580    2.926829
3.190    2.926829
3.500    2.926829
3.640    2.439024
3.520    2.439024
3.860    1.951220
3.540    1.951220
3.470    1.951220
3.255    1.951220
3.900    1.463415
2.900    1.463415
3.100    0.975610
4.170    0.975610
2.800    0.975610
2.190    0.975610
3.080    0.975610
2.680    0.975610
2.360    0.487805
3.160    0.487805
2.070    0.487805
3.210    0.487805
3.120    0.487805
2.760    0.487805
2.870    0.487805
Name: stroke, dtype: float64
3.400    20
3.230    14
3.150    14
3.030    14
3.390    13
2.640    11
3.290     9
3.350     9
3.460     8
3.110     6
3.270     6
3.410     6
3.070     6
3.580     6
3.190     6
3.500     6
3.640     5
3.520     5
3.860     4
3.540     4
3.470     4
3.255     4
3.900     3
2.900     3
3.100     2
4.170     2
2.800     2
2.190     2
3.080     2
2.680     2
2.360     1
3.160     1
2.070     1
3.210     1
3.120     1
2.760     1
2.870     1
Name: stroke, dtype: int64
--------------------------------
Column Name: compressionratio
--------------------------------
9.00     22.439024
9.40     12.682927
8.50      6.829268
9.50      6.341463
9.30      5.365854
8.70      4.390244
8.00      3.902439
9.20      3.902439
7.00      3.414634
8.60      2.439024
21.00     2.439024
8.40      2.439024
7.50      2.439024
23.00     2.439024
9.60      2.439024
21.50     1.951220
7.60      1.951220
10.00     1.463415
22.50     1.463415
8.30      1.463415
8.80      1.463415
7.70      0.975610
8.10      0.975610
9.10      0.487805
9.31      0.487805
7.80      0.487805
9.41      0.487805
21.90     0.487805
22.00     0.487805
22.70     0.487805
10.10     0.487805
11.50     0.487805
Name: compressionratio, dtype: float64
9.00     46
9.40     26
8.50     14
9.50     13
9.30     11
8.70      9
8.00      8
9.20      8
7.00      7
8.60      5
21.00     5
8.40      5
7.50      5
23.00     5
9.60      5
21.50     4
7.60      4
10.00     3
22.50     3
8.30      3
8.80      3
7.70      2
8.10      2
9.10      1
9.31      1
7.80      1
9.41      1
21.90     1
22.00     1
22.70     1
10.10     1
11.50     1
Name: compressionratio, dtype: int64
--------------------------------
Column Name: horsepower
--------------------------------
68     9.268293
70     5.365854
69     4.878049
116    4.390244
110    3.902439
95     3.414634
114    2.926829
160    2.926829
101    2.926829
62     2.926829
88     2.926829
145    2.439024
76     2.439024
97     2.439024
84     2.439024
90     2.439024
82     2.439024
102    2.439024
92     1.951220
111    1.951220
123    1.951220
86     1.951220
207    1.463415
73     1.463415
182    1.463415
121    1.463415
85     1.463415
152    1.463415
176    0.975610
94     0.975610
56     0.975610
112    0.975610
161    0.975610
184    0.975610
155    0.975610
156    0.975610
52     0.975610
100    0.975610
162    0.975610
140    0.487805
115    0.487805
134    0.487805
78     0.487805
142    0.487805
288    0.487805
143    0.487805
48     0.487805
200    0.487805
58     0.487805
55     0.487805
60     0.487805
175    0.487805
154    0.487805
72     0.487805
120    0.487805
64     0.487805
135    0.487805
262    0.487805
106    0.487805
Name: horsepower, dtype: float64
68     19
70     11
69     10
116     9
110     8
95      7
114     6
160     6
101     6
62      6
88      6
145     5
76      5
97      5
84      5
90      5
82      5
102     5
92      4
111     4
123     4
86      4
207     3
73      3
182     3
121     3
85      3
152     3
176     2
94      2
56      2
112     2
161     2
184     2
155     2
156     2
52      2
100     2
162     2
140     1
115     1
134     1
78      1
142     1
288     1
143     1
48      1
200     1
58      1
55      1
60      1
175     1
154     1
72      1
120     1
64      1
135     1
262     1
106     1
Name: horsepower, dtype: int64
--------------------------------
Column Name: peakrpm
--------------------------------
5500    18.048780
4800    17.560976
5000    13.170732
5200    11.219512
5400     6.341463
6000     4.390244
4500     3.414634
5800     3.414634
5250     3.414634
5100     2.439024
4150     2.439024
4200     2.439024
4350     1.951220
4750     1.951220
5900     1.463415
4250     1.463415
4400     1.463415
6600     0.975610
4650     0.487805
5600     0.487805
5750     0.487805
4900     0.487805
5300     0.487805
Name: peakrpm, dtype: float64
5500    37
4800    36
5000    27
5200    23
5400    13
6000     9
4500     7
5800     7
5250     7
5100     5
4150     5
4200     5
4350     4
4750     4
5900     3
4250     3
4400     3
6600     2
4650     1
5600     1
5750     1
4900     1
5300     1
Name: peakrpm, dtype: int64
--------------------------------
Column Name: citympg
--------------------------------
31    13.658537
19    13.170732
24    10.731707
27     6.829268
17     6.341463
26     5.853659
23     5.853659
21     3.902439
25     3.902439
30     3.902439
38     3.414634
28     3.414634
16     2.926829
37     2.926829
22     1.951220
29     1.463415
15     1.463415
20     1.463415
18     1.463415
14     0.975610
34     0.487805
35     0.487805
32     0.487805
36     0.487805
45     0.487805
13     0.487805
49     0.487805
47     0.487805
33     0.487805
Name: citympg, dtype: float64
31    28
19    27
24    22
27    14
17    13
26    12
23    12
21     8
25     8
30     8
38     7
28     7
16     6
37     6
22     4
29     3
15     3
20     3
18     3
14     2
34     1
35     1
32     1
36     1
45     1
13     1
49     1
47     1
33     1
Name: citympg, dtype: int64
--------------------------------
Column Name: highwaympg
--------------------------------
25    9.268293
38    8.292683
24    8.292683
30    7.804878
32    7.804878
34    6.829268
37    6.341463
28    6.341463
29    4.878049
33    4.390244
22    3.902439
31    3.902439
23    3.414634
27    2.439024
43    1.951220
42    1.463415
26    1.463415
41    1.463415
19    0.975610
39    0.975610
18    0.975610
16    0.975610
20    0.975610
36    0.975610
47    0.975610
46    0.975610
54    0.487805
17    0.487805
53    0.487805
50    0.487805
Name: highwaympg, dtype: float64
25    19
38    17
24    17
30    16
32    16
34    14
37    13
28    13
29    10
33     9
22     8
31     8
23     7
27     5
43     4
42     3
26     3
41     3
19     2
39     2
18     2
16     2
20     2
36     2
47     2
46     2
54     1
17     1
53     1
50     1
Name: highwaympg, dtype: int64
--------------------------------
Column Name: price
--------------------------------
8921.0     0.975610
9279.0     0.975610
7898.0     0.975610
8916.5     0.975610
7775.0     0.975610
             ...   
45400.0    0.487805
16503.0    0.487805
5389.0     0.487805
6189.0     0.487805
22625.0    0.487805
Name: price, Length: 189, dtype: float64
8921.0     2
9279.0     2
7898.0     2
8916.5     2
7775.0     2
          ..
45400.0    1
16503.0    1
5389.0     1
6189.0     1
22625.0    1
Name: price, Length: 189, dtype: int64


cars.loc[cars['carbody'].isnull()]


cars['carbody'] = np.where(
   (cars['CarName'] =='audi 100 ls') & (cars['carbody'].isnull()) , 'sedan', cars['carbody'])


cars['carbody'] = np.where(
   (cars['CarName'] =='audi 100ls') & (cars['carbody'].isnull()) , 'sedan', cars['carbody'])


cars['carbody'].fillna (value='sedan', inplace = True)


pd.set_option('display.max_rows',20000, 'display.max_columns',100)


cars['CarName'].value_counts().sort_index(ascending=True)

Nissan versa                       1
alfa-romero Quadrifoglio           1
alfa-romero giulia                 1
alfa-romero stelvio                1
audi 100 ls                        1
audi 100ls                         2
audi 4000                          1
audi 5000                          1
audi 5000s (diesel)                1
audi fox                           1
bmw 320i                           2
bmw x1                             1
bmw x3                             2
bmw x4                             1
bmw x5                             1
bmw z4                             1
buick century                      1
buick century luxus (sw)           1
buick century special              1
buick electra 225 custom           1
buick opel isuzu deluxe            1
buick regal sport coupe (turbo)    1
buick skyhawk                      1
buick skylark                      1
chevrolet impala                   1
chevrolet monte carlo              1
chevrolet vega 2300                1
dodge challenger se                1
dodge colt (sw)                    1
dodge colt hardtop                 1
dodge coronet custom               1
dodge coronet custom (sw)          1
dodge d200                         1
dodge dart custom                  1
dodge monaco (sw)                  1
dodge rampage                      1
honda accord                       2
honda accord cvcc                  1
honda accord lx                    1
honda civic                        3
honda civic (auto)                 1
honda civic 1300                   1
honda civic 1500 gl                1
honda civic cvcc                   2
honda prelude                      1
isuzu D-Max                        2
isuzu D-Max V-Cross                1
isuzu MU-X                         1
jaguar xf                          1
jaguar xj                          1
jaguar xk                          1
maxda glc deluxe                   1
maxda rx3                          1
mazda 626                          3
mazda glc                          2
mazda glc 4                        1
mazda glc custom                   1
mazda glc custom l                 1
mazda glc deluxe                   2
mazda rx-4                         2
mazda rx-7 gs                      2
mazda rx2 coupe                    1
mercury cougar                     1
mitsubishi g4                      3
mitsubishi lancer                  1
mitsubishi mirage                  1
mitsubishi mirage g4               3
mitsubishi montero                 1
mitsubishi outlander               3
mitsubishi pajero                  1
nissan clipper                     2
nissan dayz                        1
nissan fuga                        1
nissan gt-r                        1
nissan juke                        1
nissan kicks                       1
nissan latio                       2
nissan leaf                        1
nissan note                        1
nissan nv200                       1
nissan otti                        1
nissan rogue                       2
nissan teana                       1
nissan titan                       1
peugeot 304                        1
peugeot 504                        6
peugeot 504 (sw)                   1
peugeot 505s turbo diesel          1
peugeot 604sl                      2
plymouth cricket                   1
plymouth duster                    1
plymouth fury gran sedan           1
plymouth fury iii                  2
plymouth satellite custom (sw)     1
plymouth valiant                   1
porcshce panamera                  1
porsche boxter                     1
porsche cayenne                    2
porsche macan                      1
renault 12tl                       1
renault 5 gtl                      1
saab 99e                           2
saab 99gle                         2
saab 99le                          2
subaru                             2
subaru baja                        1
subaru brz                         1
subaru dl                          4
subaru r1                          1
subaru r2                          1
subaru trezia                      1
subaru tribeca                     1
toyota carina                      1
toyota celica gt                   1
toyota celica gt liftback          1
toyota corolla                     6
toyota corolla 1200                2
toyota corolla 1600 (sw)           1
toyota corolla liftback            2
toyota corolla tercel              1
toyota corona                      6
toyota corona hardtop              1
toyota corona liftback             1
toyota corona mark ii              1
toyota cressida                    1
toyota mark ii                     3
toyota starlet                     2
toyota tercel                      1
toyouta tercel                     1
vokswagen rabbit                   1
volkswagen 1131 deluxe sedan       1
volkswagen 411 (sw)                1
volkswagen dasher                  2
volkswagen model 111               1
volkswagen rabbit                  1
volkswagen rabbit custom           1
volkswagen super beetle            1
volkswagen type 3                  1
volvo 144ea                        2
volvo 145e (sw)                    2
volvo 244dl                        2
volvo 245                          1
volvo 246                          1
volvo 264gl                        2
volvo diesel                       1
vw dasher                          1
vw rabbit                          1
Name: CarName, dtype: int64


cars['CarName'].unique()

array(['alfa-romero giulia', 'alfa-romero stelvio',
       'alfa-romero Quadrifoglio', 'audi 100 ls', 'audi 100ls',
       'audi fox', 'audi 5000', 'audi 4000', 'audi 5000s (diesel)',
       'bmw 320i', 'bmw x1', 'bmw x3', 'bmw z4', 'bmw x4', 'bmw x5',
       'chevrolet impala', 'chevrolet monte carlo', 'chevrolet vega 2300',
       'dodge rampage', 'dodge challenger se', 'dodge d200',
       'dodge monaco (sw)', 'dodge colt hardtop', 'dodge colt (sw)',
       'dodge coronet custom', 'dodge dart custom',
       'dodge coronet custom (sw)', 'honda civic', 'honda civic cvcc',
       'honda accord cvcc', 'honda accord lx', 'honda civic 1500 gl',
       'honda accord', 'honda civic 1300', 'honda prelude',
       'honda civic (auto)', 'isuzu MU-X', 'isuzu D-Max ',
       'isuzu D-Max V-Cross', 'jaguar xj', 'jaguar xf', 'jaguar xk',
       'maxda rx3', 'maxda glc deluxe', 'mazda rx2 coupe', 'mazda rx-4',
       'mazda glc deluxe', 'mazda 626', 'mazda glc', 'mazda rx-7 gs',
       'mazda glc 4', 'mazda glc custom l', 'mazda glc custom',
       'buick electra 225 custom', 'buick century luxus (sw)',
       'buick century', 'buick skyhawk', 'buick opel isuzu deluxe',
       'buick skylark', 'buick century special',
       'buick regal sport coupe (turbo)', 'mercury cougar',
       'mitsubishi mirage', 'mitsubishi lancer', 'mitsubishi outlander',
       'mitsubishi g4', 'mitsubishi mirage g4', 'mitsubishi montero',
       'mitsubishi pajero', 'Nissan versa', 'nissan gt-r', 'nissan rogue',
       'nissan latio', 'nissan titan', 'nissan leaf', 'nissan juke',
       'nissan note', 'nissan clipper', 'nissan nv200', 'nissan dayz',
       'nissan fuga', 'nissan otti', 'nissan teana', 'nissan kicks',
       'peugeot 504', 'peugeot 304', 'peugeot 504 (sw)', 'peugeot 604sl',
       'peugeot 505s turbo diesel', 'plymouth fury iii',
       'plymouth cricket', 'plymouth satellite custom (sw)',
       'plymouth fury gran sedan', 'plymouth valiant', 'plymouth duster',
       'porsche macan', 'porcshce panamera', 'porsche cayenne',
       'porsche boxter', 'renault 12tl', 'renault 5 gtl', 'saab 99e',
       'saab 99le', 'saab 99gle', 'subaru', 'subaru dl', 'subaru brz',
       'subaru baja', 'subaru r1', 'subaru r2', 'subaru trezia',
       'subaru tribeca', 'toyota corona mark ii', 'toyota corona',
       'toyota corolla 1200', 'toyota corona hardtop',
       'toyota corolla 1600 (sw)', 'toyota carina', 'toyota mark ii',
       'toyota corolla', 'toyota corolla liftback',
       'toyota celica gt liftback', 'toyota corolla tercel',
       'toyota corona liftback', 'toyota starlet', 'toyota tercel',
       'toyota cressida', 'toyota celica gt', 'toyouta tercel',
       'vokswagen rabbit', 'volkswagen 1131 deluxe sedan',
       'volkswagen model 111', 'volkswagen type 3', 'volkswagen 411 (sw)',
       'volkswagen super beetle', 'volkswagen dasher', 'vw dasher',
       'vw rabbit', 'volkswagen rabbit', 'volkswagen rabbit custom',
       'volvo 145e (sw)', 'volvo 144ea', 'volvo 244dl', 'volvo 245',
       'volvo 264gl', 'volvo diesel', 'volvo 246'], dtype=object)


cars["CarName"] = np.where(cars["CarName"] == "vw dasher", "volkswagen dasher", cars["CarName"])
cars["CarName"] = np.where(cars["CarName"] == "vw rabbit", "volkswagen rabbit", cars["CarName"])
cars["CarName"] = np.where(cars["CarName"] == "vokswagen rabbit", "volkswagen rabbit", cars["CarName"])

cars["CarName"] = np.where(cars["CarName"] == "toyouta tercel", "toyota tercel", cars["CarName"])
cars["CarName"] = np.where(cars["CarName"] == "toyota corona", "toyota corolla", cars["CarName"])

cars["CarName"] = np.where(cars["CarName"] == "toyota corona hardtop", "toyota corolla hardtop", cars["CarName"])
cars["CarName"] = np.where(cars["CarName"] == "toyota corona liftback", "toyota corolla liftback", cars["CarName"])
cars["CarName"] = np.where(cars["CarName"] == "toyota corona mark ii", "toyota corolla mark ii", cars["CarName"])
cars["CarName"] = np.where(cars["CarName"] == "maxda glc deluxe", "mazda glc deluxe", cars["CarName"])
cars["CarName"] = np.where(cars["CarName"] == "maxda rx3", "mazda rx3", cars["CarName"])

cars["CarName"] = np.where(cars["CarName"] == "audi 100 ls", "audi 100ls", cars["CarName"])
cars["CarName"] = np.where(cars["CarName"] == "porcshce panamera", "porsche panamera", cars["CarName"])


CompanyName = cars['CarName'].apply(lambda x : x.split(' ')[0])

cars.insert(3,"CompanyName",CompanyName)


cars.drop(['car_ID'],axis=1,inplace=True)


cars


cars['CompanyName'].value_counts()

toyota         32
mazda          17
nissan         17
mitsubishi     13
honda          13
volkswagen     12
subaru         12
peugeot        11
volvo          11
dodge           9
buick           8
bmw             8
audi            7
plymouth        7
saab            6
porsche         5
isuzu           4
jaguar          3
chevrolet       3
alfa-romero     3
renault         2
mercury         1
Nissan          1
Name: CompanyName, dtype: int64


cars = cars.replace(to_replace ="maxda", value ="mazda")


plt.title('Car Price Spread')
sns.boxplot(y=cars.price)
plt.show()
print(cars.price.describe())

count      205.000000
mean     13276.710571
std       7988.852332
min       5118.000000
25%       7788.000000
50%      10295.000000
75%      16503.000000
max      45400.000000
Name: price, dtype: float64


plt.title('Car Price Distribution Plot')
sns.distplot(cars.price)
plt.show()


plt.figure(figsize=(20,8))

plt.subplot(1,2,1)
plt.title('Car Price Distribution Plot')
sns.distplot(cars.price)

plt.subplot(1,2,2)
plt.title('Car Price Spread')
sns.boxplot(y=cars.price)

plt.show()
print(cars.price.describe())

count      205.000000
mean     13276.710571
std       7988.852332
min       5118.000000
25%       7788.000000
50%      10295.000000
75%      16503.000000
max      45400.000000
Name: price, dtype: float64


company  = cars['CompanyName'].value_counts()
company = company[:10,]
plt.figure(figsize=(10,5))
sns.barplot(company.index, company.values, alpha=0.8)
plt.title('Company')
plt.ylabel('Number of Occurrences', fontsize=12)
plt.xlabel('Company', fontsize=12)
plt.show()


company  = cars['CompanyName'].value_counts()
plt.figure(figsize=(10,5))
sns.barplot(company.index, company.values, alpha=0.8)
plt.title('Company')
plt.ylabel('Number of Occurrences', fontsize=12)
plt.xlabel('Company', fontsize=12)
plt.xticks(rotation = 40)
plt.show()


def plot_count(x,fig):
    plt.subplot(4,2,fig)
    plt.title(x+' Histogram')
    sns.countplot(cars[x],palette=("magma"))
    plt.subplot(4,2,(fig+1))
    plt.title(x+' vs Price')
    sns.boxplot(x=cars[x], y=cars.price, palette=("magma"))
    
plt.figure(figsize=(15,20))

plot_count('enginelocation', 1)
plot_count('cylindernumber', 3)
plot_count('fuelsystem', 5)
plot_count('drivewheel', 7)

plt.tight_layout()


def scatter(x,fig):
    plt.subplot(5,2,fig)
    plt.scatter(cars[x],cars['price'])
    plt.title(x+' vs Price')
    plt.ylabel('Price')
    plt.xlabel(x)

plt.figure(figsize=(10,20))

scatter('carlength', 1)
scatter('carwidth', 2)
scatter('carheight', 3)
scatter('curbweight', 4)

plt.tight_layout()


#Binning the Car Companies based on avg prices of each Company.
cars['price'] = cars['price'].astype('int')
bins = [0,10000,20000,40000]
cars_bin=['Budget','Medium','Highend']
cars['carsrange_binned'] = pd.cut(cars['price'],bins,right=False,labels=cars_bin)
cars.head()


cars_new = cars[['price', 'fueltype', 'aspiration','carbody', 'drivewheel','wheelbase',
                  'curbweight', 'enginetype', 'cylindernumber', 'enginesize', 'boreratio','horsepower', 
                     'carlength','carwidth', 'carsrange_binned']]
cars_new.head()
sns.pairplot(cars_new)
plt.show()


c = ['#F1C40F', '#3498DB',"#9b59b6"]
labels = ['Budget','Medium','Highend']

patches, texts, pcts=plt.pie(cars['carsrange_binned'].value_counts(),labels =labels,colors=c, autopct='%.1f%%' ,
         wedgeprops={'linewidth': 5.0, 'edgecolor': 'white'},textprops={'size': '15', 'color':'black'})
plt.setp(texts, fontweight=700)

for i, color in enumerate(c):
    texts[i].set_color(color)


plt.figure(figsize=(15,10))
sns.countplot(x='carbody', data = cars,
              order=pd.value_counts(cars['carbody']).index, palette='BuGn_r')
plt.title('Number of Cars grouped by carbody', weight='bold')
plt.xlabel('Type', fontsize=12)
plt.ylabel('Count', fontsize=12)

Text(0, 0.5, 'Count')


fig, ax1 = plt.subplots(figsize=(20,10))
graph = sns.countplot(ax=ax1,x='carbody', data=cars, order=pd.value_counts(cars['carbody']).index, palette='BuGn_r')
graph.set_xticklabels(graph.get_xticklabels())
i=0
for p in graph.patches:
    height = p.get_height()
    graph.text(p.get_x()+p.get_width()/2., height + 0.1,
        cars['carbody'].value_counts()[i],ha="center")
    i += 1

plt.xlabel('Carbody TYpe', fontsize=12)
plt.ylabel('Count', fontsize=12)
plt.title('Number of Cars grouped by carbody', weight='bold')

Text(0.5, 1.0, 'Number of Cars grouped by carbody')


cars['carbody'].value_counts()

sedan          96
hatchback      70
wagon          25
hardtop         8
convertible     6
Name: carbody, dtype: int64


#df['adr'] = df['adr'].astype(float)
from numpy import mean
plt.figure(figsize=(15,10))
sns.barplot(x='carbody', y='citympg', hue='carsrange_binned', dodge=True, palette= 'PuBu_r', data=cars,estimator=mean,ci = None)
plt.title('Price Range grouped by Carbody and Fueltype', weight='bold')
plt.xlabel('Carbody', fontsize=12)
plt.ylabel('citympg', fontsize=12)

Text(0, 0.5, 'citympg')


from numpy import mean
plt.figure(figsize=(15,10))
sns.barplot(x='carbody', y='price',  palette= 'PuBu_r', data=cars,estimator=mean,ci = None)
plt.title('Price ', weight='bold')
plt.xlabel('Carbody', fontsize=12)
plt.ylabel('price', fontsize=12)

Text(0, 0.5, 'price')


plt.figure(figsize=(10,8))
sns.countplot(x='carbody',order=pd.value_counts(cars['carbody']).index,hue='fueltype',data=cars)
plt.xticks(rotation = 40)
plt.show()


plt.figure(figsize=(10,6))
sns.kdeplot(cars.citympg, shade=True,color="r")
plt.xlim((0,54))
plt.title("Density plot on City Mileage")
plt.ylabel("Density")
plt.xlabel('City Mileage')
plt.grid(True)
plt.show()


plt.figure(figsize=(10,6))
fig = sns.kdeplot(cars['citympg'], shade=True, color="r")
fig = sns.kdeplot(cars['highwaympg'], shade=True, color="b")
plt.grid(True)
plt.show()


plt.figure(figsize=(15,10))
sns.lineplot(data = cars, x = 'enginesize', y = 'horsepower', hue = 'carsrange_binned')
plt.title("Engine Size and Horsepower by Price Range")
plt.ylabel("Horse Power")
plt.xlabel('Engine Size')
plt.show()


cars.enginesize.hist(bins=10, alpha=0.5)
plt.title(" Histogram")
plt.xlabel("Engine Size")
plt.ylabel("Frequency")

Text(0, 0.5, 'Frequency')


corrmat=cars.corr()
top_corr_feature=corrmat.index
plt.figure(figsize=(20,20))
g=sns.heatmap(cars[top_corr_feature].corr(), annot=True,cmap="RdYlGn")


num = cars.select_dtypes(exclude = 'object')
numcorr = cars.corr()
f, ax = plt.subplots(figsize = (19,1)) # set figure size
sns.heatmap(numcorr.sort_values(by = 'price', ascending = False).head(1), annot = True, fmt = ".2f")
plt.show()


numcorr['price'].sort_values(ascending = False).to_frame().plot.bar(color = 'blue')
plt.axhline(y = 0.5, color = 'r', linestyle = '-')
plt.title('Corrplot vs. Price')
plt.show()


#cars.to_excel("cars_cleaned.xlsx",sheet_name='Cleaned')


list5 = []
for index,row in cars.iterrows():
    if len(row.doornumber) > 1:
        list5.append(w2n.word_to_num(row.doornumber))
    else:
        list5.append('4')


cars['doornumber_int'] = pd.Series(list5)


cars['doornumber_int'].unique()

array([2, 4], dtype=int64)


cars.drop(['doornumber'],axis=1,inplace=True)


list6 = []
for index,row in cars.iterrows():
    if len(row.cylindernumber) > 1:
        list6.append(w2n.word_to_num(row.cylindernumber))
    else:
        list6.append('4')


cars['cylindernumber_int'] = pd.Series(list6)


cars['cylindernumber_int'].unique()

array([ 4,  6,  5,  3, 12,  2,  8], dtype=int64)


cars.drop(['cylindernumber'],axis=1,inplace=True)


#split the dependent variable and independent variable
cars_X =  cars.copy()
cars_X.drop(['price'],axis=1,inplace=True)
cars_y = cars['price']


cars_x= cars_X.iloc[:,:].values


type(cars_x)

numpy.ndarray


cars.head(1)


list(cars_x[1,:])

[3,
 'alfa-romero stelvio',
 'alfa-romero',
 'gas',
 'std',
 'convertible',
 'rwd',
 'front',
 88.6,
 168.8,
 64.1,
 48.8,
 2548,
 'dohc',
 130,
 'mpfi',
 3.47,
 2.68,
 9.0,
 111,
 5000,
 21,
 27,
 'Medium',
 2,
 4]


#list all the categorical variables
columns_ohe = [1,2,3,4,5,6,7,13,15,23]


list(cars_x[1,[1,2,3,4,5,6,7,13,15,23]])

['alfa-romero stelvio',
 'alfa-romero',
 'gas',
 'std',
 'convertible',
 'rwd',
 'front',
 'dohc',
 'mpfi',
 'Medium']


for num in tqdm(columns_ohe):
    dummy_ = pd.get_dummies(cars_x[:,num],sparse=True)
    if(num!=1):
        dummy = np.concatenate((dummy,dummy_),axis=1)
    else:
        dummy = dummy_

100%|█████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 303.84it/s]


list(cars_x[1,:])

[3,
 'alfa-romero stelvio',
 'alfa-romero',
 'gas',
 'std',
 'convertible',
 'rwd',
 'front',
 88.6,
 168.8,
 64.1,
 48.8,
 2548,
 'dohc',
 130,
 'mpfi',
 3.47,
 2.68,
 9.0,
 111,
 5000,
 21,
 27,
 'Medium',
 2,
 4]


cars_x = np.delete(cars_x,columns_ohe,1)


cars_x = np.concatenate((cars_x,dummy),axis=1)


list(cars_x[1,:])

[3,
 88.6,
 168.8,
 64.1,
 48.8,
 2548,
 130,
 3.47,
 2.68,
 9.0,
 111,
 5000,
 21,
 27,
 2,
 4,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 1,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 1,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 1]


np.random.seed(0)
number_of_samples = len(cars_x)
random_indices = np.random.permutation(number_of_samples)
num_training_samples = int(number_of_samples*0.75)
cars_x_train = cars_x[random_indices[:num_training_samples]]
cars_y_train=cars_y[random_indices[:num_training_samples]]
cars_x_validation=cars_x[random_indices[num_training_samples:]]
cars_y_validation=cars_y[random_indices[num_training_samples:]]


len(cars_x_train)

153


len(cars_y_train)

153


len(cars_x_validation)

52


len(cars_y_validation)

52


from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
# Fit on training set only.
scaler.fit(cars_x_train)
# Apply transform to both thvfe training set and the test set.
cars_x_train = scaler.transform(cars_x_train)
cars_x_validation = scaler.transform(cars_x_validation)


cars_x_train.shape

(153, 210)


cars_x_validation.shape

(52, 210)


from sklearn.decomposition import PCA
# Make an instance of the Model
pca = PCA(.95)
pca.fit(cars_x_train)
cars_x_train = pca.transform(cars_x_train)
cars_x_validation = pca.transform(cars_x_validation)


cars_x_train.shape

(153, 107)


cars_x_validation.shape

(52, 107)


from sklearn.linear_model import LinearRegression
model = LinearRegression()
model.fit(cars_x_train, cars_y_train)
cars_linear_train_predicted = model.predict(cars_x_train)
cars_linear_validation_predicted = model.predict(cars_x_validation)


from sklearn.metrics import r2_score,mean_squared_error
r2_score(cars_y_train, cars_linear_train_predicted)


r2_score(cars_y_validation, cars_linear_validation_predicted)


# The coefficients
#print("Coefficients: \n", model.coef_)
# The mean squared error
print("Training data -Mean squared error: %.2f" % mean_squared_error(cars_y_train, cars_linear_train_predicted))
print("Validation data - Mean squared error: %.2f" % mean_squared_error(cars_y_validation, cars_linear_validation_predicted))
# The coefficient of determination: 1 is perfect prediction
print("Training data Coefficient of determination: %.2f" % r2_score(cars_y_train, cars_linear_train_predicted))
print("Validation data Coefficient of determination: %.2f" % r2_score(cars_y_validation, cars_linear_validation_predicted))

# Plot outputs
plt.scatter(cars_y_train, cars_linear_train_predicted, color="black")
plt.scatter(cars_y_validation, cars_linear_validation_predicted, color="red")

#plt.plot(cars_y_validation, cars_linear_validation_predicted, color="blue", linewidth=3)

plt.xticks(())
plt.yticks(())
plt.title(" Dot Chart")
plt.xlabel("Actual Data")
plt.ylabel("Predicted Data")

plt.show()

	car_ID	symboling	wheelbase	carlength	carwidth	carheight	curbweight	enginesize	boreratio	stroke	compressionratio	horsepower	peakrpm	citympg	highwaympg	price
count	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000
mean	103.000000	0.834146	98.756585	174.049268	65.907805	53.724878	2555.565854	126.907317	3.329756	3.255415	10.142537	104.117073	5125.121951	25.219512	30.751220	13276.710571
std	59.322565	1.245307	6.021776	12.337289	2.145204	2.443522	520.680204	41.642693	0.270844	0.313597	3.972040	39.544167	476.985643	6.542142	6.886443	7988.852332
min	1.000000	-2.000000	86.600000	141.100000	60.300000	47.800000	1488.000000	61.000000	2.540000	2.070000	7.000000	48.000000	4150.000000	13.000000	16.000000	5118.000000
25%	52.000000	0.000000	94.500000	166.300000	64.100000	52.000000	2145.000000	97.000000	3.150000	3.110000	8.600000	70.000000	4800.000000	19.000000	25.000000	7788.000000
50%	103.000000	1.000000	97.000000	173.200000	65.500000	54.100000	2414.000000	120.000000	3.310000	3.290000	9.000000	95.000000	5200.000000	24.000000	30.000000	10295.000000
75%	154.000000	2.000000	102.400000	183.100000	66.900000	55.500000	2935.000000	141.000000	3.580000	3.410000	9.400000	116.000000	5500.000000	30.000000	34.000000	16503.000000
max	205.000000	3.000000	120.900000	208.100000	72.300000	59.800000	4066.000000	326.000000	3.940000	4.170000	23.000000	288.000000	6600.000000	49.000000	54.000000	45400.000000

	count	mean	std	min	25%	50%	75%	max
car_ID	205.0	103.000000	59.322565	1.00	52.00	103.00	154.00	205.00
symboling	205.0	0.834146	1.245307	-2.00	0.00	1.00	2.00	3.00
wheelbase	205.0	98.756585	6.021776	86.60	94.50	97.00	102.40	120.90
carlength	205.0	174.049268	12.337289	141.10	166.30	173.20	183.10	208.10
carwidth	205.0	65.907805	2.145204	60.30	64.10	65.50	66.90	72.30
carheight	205.0	53.724878	2.443522	47.80	52.00	54.10	55.50	59.80
curbweight	205.0	2555.565854	520.680204	1488.00	2145.00	2414.00	2935.00	4066.00
enginesize	205.0	126.907317	41.642693	61.00	97.00	120.00	141.00	326.00
boreratio	205.0	3.329756	0.270844	2.54	3.15	3.31	3.58	3.94
stroke	205.0	3.255415	0.313597	2.07	3.11	3.29	3.41	4.17
compressionratio	205.0	10.142537	3.972040	7.00	8.60	9.00	9.40	23.00
horsepower	205.0	104.117073	39.544167	48.00	70.00	95.00	116.00	288.00
peakrpm	205.0	5125.121951	476.985643	4150.00	4800.00	5200.00	5500.00	6600.00
citympg	205.0	25.219512	6.542142	13.00	19.00	24.00	30.00	49.00
highwaympg	205.0	30.751220	6.886443	16.00	25.00	30.00	34.00	54.00
price	205.0	13276.710571	7988.852332	5118.00	7788.00	10295.00	16503.00	45400.00

Visualizations¶

Feature Engineering¶

One Hot Encoding¶

Data Splitting¶

Standard Scaling¶

Principal Component Analysis¶

Linear Regression¶

	car_ID	symboling	CarName	fueltype	aspiration	doornumber	carbody	drivewheel	enginelocation	wheelbase	...	enginesize	fuelsystem	boreratio	stroke	compressionratio	horsepower	peakrpm	citympg	highwaympg	price
0	1	3	alfa-romero giulia	gas	std	two	convertible	rwd	front	88.6	...	130	mpfi	3.47	2.68	9.0	111	5000	21	27	13495.0
1	2	3	alfa-romero stelvio	gas	std	two	convertible	rwd	front	88.6	...	130	mpfi	3.47	2.68	9.0	111	5000	21	27	16500.0

	car_ID	symboling	CarName	fueltype	aspiration	doornumber	carbody	drivewheel	enginelocation	wheelbase	...	enginesize	fuelsystem	boreratio	stroke	compressionratio	horsepower	peakrpm	citympg	highwaympg	price
200	201	-1	volvo 145e (sw)	gas	std	four	sedan	rwd	front	109.1	...	141	mpfi	3.78	3.15	9.5	114	5400	23	28	16845.0
201	202	-1	volvo 144ea	gas	turbo	four	sedan	rwd	front	109.1	...	141	mpfi	3.78	3.15	8.7	160	5300	19	25	19045.0
202	203	-1	volvo 244dl	gas	std	four	sedan	rwd	front	109.1	...	173	mpfi	3.58	2.87	8.8	134	5500	18	23	21485.0
203	204	-1	volvo 246	diesel	turbo	four	sedan	rwd	front	109.1	...	145	idi	3.01	3.40	23.0	106	4800	26	27	22470.0
204	205	-1	volvo 264gl	gas	turbo	four	sedan	rwd	front	109.1	...	141	mpfi	3.78	3.15	9.5	114	5400	19	25	22625.0

	count	unique	top	freq
CarName	205	147	toyota corona	6
fueltype	194	2	gas	174
aspiration	205	2	std	168
doornumber	205	2	four	115
carbody	200	5	sedan	91
drivewheel	205	3	fwd	120
enginelocation	193	2	front	190
enginetype	205	7	ohc	148
cylindernumber	205	7	four	159
fuelsystem	205	8	mpfi	94

	car_ID	symboling	CarName	fueltype
0	1	3	alfa-romero giulia	gas
1	2	3	alfa-romero stelvio	gas
2	3	1	alfa-romero Quadrifoglio	gas
3	4	2	audi 100 ls	gas
4	5	2	audi 100ls	gas

	symboling	CarName	CompanyName	fueltype	aspiration	doornumber	carbody	drivewheel	enginelocation	wheelbase	carlength	carwidth	carheight	curbweight	enginetype	cylindernumber	enginesize	fuelsystem	boreratio	stroke	compressionratio	horsepower	peakrpm	citympg	highwaympg	price	carsrange_binned
0	3	alfa-romero giulia	alfa-romero	gas	std	two	convertible	rwd	front	88.6	168.8	64.1	48.8	2548	dohc	four	130	mpfi	3.47	2.68	9.0	111	5000	21	27	13495	Medium
1	3	alfa-romero stelvio	alfa-romero	gas	std	two	convertible	rwd	front	88.6	168.8	64.1	48.8	2548	dohc	four	130	mpfi	3.47	2.68	9.0	111	5000	21	27	16500	Medium
2	1	alfa-romero Quadrifoglio	alfa-romero	gas	std	two	hatchback	rwd	front	94.5	171.2	65.5	52.4	2823	ohcv	six	152	mpfi	2.68	3.47	9.0	154	5000	19	26	16500	Medium
3	2	audi 100ls	audi	gas	std	four	sedan	fwd	front	99.8	176.6	66.2	54.3	2337	ohc	four	109	mpfi	3.19	3.40	10.0	102	5500	24	30	13950	Medium
4	2	audi 100ls	audi	gas	std	four	sedan	4wd	front	99.4	176.6	66.4	54.3	2824	ohc	five	136	mpfi	3.19	3.40	8.0	115	5500	18	22	17450	Medium