-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcar_price_prediction.py
170 lines (115 loc) · 25.9 KB
/
car_price_prediction.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
# -*- coding: utf-8 -*-
"""CAR_PRICE_PREDICTION.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1ZWffrctbPLs7w7NwDN_T5J5-FGhvc3jd
# **CAR PRICE PREDICTION WITH MACHINE LEARNING**
Download **Dataset here [CAR PRICE PREDICTION](https://drive.google.com/file/d/1EUfj25s3IVVe4Kxrz1hmf9QCSzy_G6Dh/view?usp=share_link)**
### Knowing about the Dataset
**Importing the Required Libraries**
"""
# Numpy Library for Numerical Calculations
import numpy as np
# Pandas Library for Dataframe
import pandas as pd
# Math Library for Mathematical Calulations
import math
# Pickle Library for Saving the Model
import pickle
# Matplotlib and Seaborn for Plottings
import matplotlib.pyplot as plt
import seaborn as sns
# Train_Test_Split for splitting the Dataset
from sklearn.model_selection import train_test_split
# Linear Regression, Decision Tree are Models
from sklearn.linear_model import LinearRegression
from sklearn.tree import DecisionTreeRegressor
# Mean Absolute Error, R2 Score and Mean Squared Error is for Analysis of Models
from sklearn.metrics import mean_absolute_error, r2_score, mean_squared_error
from sklearn.metrics import accuracy_score
from google.colab import drive
drive.mount('/content/drive')
"""**Reading informations in the Dataset**"""
car_price = pd.read_csv("/content/drive/MyDrive/Oasis Infobyte/Data Science - Internship/Car-Price-Prediction/CarPrice.csv")
"""**Checking for null values in Data**"""
car_price.isnull().sum()
"""**Checking the First Five Values in the Data**"""
car_price.head()
"""**Checking the Last Five Values in the Data**"""
car_price.tail()
"""**Dimensions of the Dataset**"""
car_price.shape
"""**Describing the Dataset**"""
car_price.describe()
"""**Checking for the classes in the Data**"""
car_price.groupby('carbody').size()
"""**Taking the required Informations**"""
car = car_price[["symboling", "wheelbase", "carlength", "carwidth", "carheight", "curbweight", "enginesize", "boreratio", "stroke", "compressionratio", "horsepower", "peakrpm", "citympg", "highwaympg", "price"]]
car
"""**Plotting the Bivariate Bar for the Dataset**"""
def plot_bivariate_bar(dataset, cols, width, height, hspace, wspace):
dataset = dataset.select_dtypes(include = [np.int64])
plt.style.use('seaborn-whitegrid')
fig = plt.figure(figsize=(width, height))
fig.subplots_adjust(left = None, bottom = None, right = None, top = None, wspace = wspace, hspace = hspace)
rows = math.ceil(float(dataset.shape[1]) / cols)
for i, column in enumerate(dataset.columns):
ax = fig.add_subplot(rows, cols, i + 1)
ax.set_title(column)
if dataset.dtypes[column] == np.int64:
g = sns.countplot(y = column, data = dataset)
substrings = [s.get_text()[:15] for s in g.get_yticklabels()]
g.set(yticklabels = substrings)
plot_bivariate_bar(car, cols = 5, width = 20, height = 15, hspace = 0.2, wspace = 0.5)
"""**Plotting the Joint Plot for the Dataset**"""
plt.figure(figsize = (10, 10))
sns.jointplot(data = car)
plt.show()
"""**Plotting the Correlation Matrix of the Dataset**"""
plt.figure(figsize = (20, 10))
sns.set_style('darkgrid')
sns.heatmap(car.corr(), annot = True, cmap = 'viridis')
plt.show()
x = car.drop(["price"], 1)
y = car["price"]
xtrain, xtest, ytrain, ytest = train_test_split(x, y, random_state = 16, test_size = 0.25, shuffle=True)
"""### Model Building
**Creating the Model**
"""
model1 = LinearRegression()
model2 = DecisionTreeRegressor()
"""**Fitting the Model**"""
model1.fit(xtrain, ytrain)
model1.score(xtrain, ytrain)
model2.fit(xtrain, ytrain)
model2.score(xtrain, ytrain)
"""### Testing Model
**Testing the Model**
"""
Linear_predictions = model1.predict(xtest)
Decision_predictions = model2.predict(xtest)
"""**Metrics**"""
print("Linear Regression Model:")
print("************************")
print('R2_score:', r2_score(ytest, Linear_predictions))
print('Mean Absolute Error:', mean_absolute_error(ytest, Linear_predictions))
print('Mean Squared Error:', mean_squared_error(ytest, Linear_predictions))
print('Root Mean Squared Error:', np.sqrt(mean_squared_error(ytest, Linear_predictions)))
print("---------------------------------------------")
print("Decision Tree Regression Model:")
print("******************************")
print('R2_score:', r2_score(ytest, Decision_predictions))
print('Mean Absolute Error:', mean_absolute_error(ytest, Decision_predictions))
print('Mean Squared Error:', mean_squared_error(ytest, Decision_predictions))
print('Root Mean Squared Error:', np.sqrt(mean_squared_error(ytest, Decision_predictions)))
print("Accuracy of Linear Regression Model: ", model1.score(xtrain, ytrain))
print("Accuracy of Decision Tree Regression Model: ", model2.score(xtrain, ytrain))
"""### Saving Models
**Saving the Models**
"""
filename = "Linear_Regression.pkl"
pickle.dump(model1, open(filename, 'wb'))
filename = "Decision_Tree_Regressor.pkl"
pickle.dump(model2, open(filename, 'wb'))
print("Saved all Models")