Spaces:
Sleeping
Sleeping
neslisahozturk
commited on
Commit
•
2c41d18
1
Parent(s):
f412dd3
Upload 3 files
Browse files- car_predict_app.py +161 -0
- cars.xls +0 -0
- requirements.txt +4 -0
car_predict_app.py
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/usr/bin/env python
|
2 |
+
# coding: utf-8
|
3 |
+
|
4 |
+
# In[15]:
|
5 |
+
|
6 |
+
|
7 |
+
import pandas as pd
|
8 |
+
import numpy as np
|
9 |
+
import seaborn as sns
|
10 |
+
import warnings
|
11 |
+
warnings.filterwarnings("ignore")
|
12 |
+
from sklearn.linear_model import LinearRegression
|
13 |
+
from sklearn.metrics import r2_score,mean_squared_error
|
14 |
+
from sklearn.compose import ColumnTransformer
|
15 |
+
from sklearn.preprocessing import OneHotEncoder, StandardScaler
|
16 |
+
from sklearn.pipeline import Pipeline
|
17 |
+
from sklearn.model_selection import train_test_split
|
18 |
+
|
19 |
+
|
20 |
+
# In[4]:
|
21 |
+
|
22 |
+
|
23 |
+
pip install xldr
|
24 |
+
|
25 |
+
|
26 |
+
# In[6]:
|
27 |
+
|
28 |
+
|
29 |
+
ls
|
30 |
+
|
31 |
+
|
32 |
+
# In[7]:
|
33 |
+
|
34 |
+
|
35 |
+
df=pd.read_excel("cars.xls")
|
36 |
+
|
37 |
+
|
38 |
+
# In[8]:
|
39 |
+
|
40 |
+
|
41 |
+
df.head()
|
42 |
+
|
43 |
+
|
44 |
+
# In[9]:
|
45 |
+
|
46 |
+
|
47 |
+
#veri ön işleme,standartlıştırma
|
48 |
+
|
49 |
+
|
50 |
+
# In[10]:
|
51 |
+
|
52 |
+
|
53 |
+
X=df.drop("Price",axis=1)
|
54 |
+
|
55 |
+
|
56 |
+
# In[13]:
|
57 |
+
|
58 |
+
|
59 |
+
y=df["Price"]
|
60 |
+
|
61 |
+
|
62 |
+
# In[16]:
|
63 |
+
|
64 |
+
|
65 |
+
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)
|
66 |
+
|
67 |
+
|
68 |
+
# In[17]:
|
69 |
+
|
70 |
+
|
71 |
+
preprocess=ColumnTransformer(
|
72 |
+
transformers=[
|
73 |
+
("num",StandardScaler(),["Mileage","Cylinder","Liter","Doors"]),
|
74 |
+
("cat",OneHotEncoder(),["Make","Model","Trim","Type"])
|
75 |
+
]
|
76 |
+
)
|
77 |
+
|
78 |
+
|
79 |
+
# In[20]:
|
80 |
+
|
81 |
+
|
82 |
+
my_model=LinearRegression()
|
83 |
+
pipe=Pipeline(steps=[("preprocessor",preprocess),("model",my_model)])
|
84 |
+
|
85 |
+
|
86 |
+
# In[21]:
|
87 |
+
|
88 |
+
|
89 |
+
pipe.fit(X_train,y_train)
|
90 |
+
|
91 |
+
|
92 |
+
# In[24]:
|
93 |
+
|
94 |
+
|
95 |
+
y_pred=pipe.predict(X_test)
|
96 |
+
rmse=mean_squared_error(y_test,y_pred)**0.5
|
97 |
+
r2=r2_score(y_test,y_pred)
|
98 |
+
r2,rmse
|
99 |
+
|
100 |
+
|
101 |
+
# In[25]:
|
102 |
+
|
103 |
+
|
104 |
+
#modeli yayma, kullanıma sunma
|
105 |
+
|
106 |
+
|
107 |
+
# ### Streamlit
|
108 |
+
|
109 |
+
# In[28]:
|
110 |
+
|
111 |
+
|
112 |
+
get_ipython().system('pip install streamlit')
|
113 |
+
|
114 |
+
|
115 |
+
# In[29]:
|
116 |
+
|
117 |
+
|
118 |
+
import streamlit as st
|
119 |
+
|
120 |
+
|
121 |
+
# In[34]:
|
122 |
+
|
123 |
+
|
124 |
+
def price(make,model,trim,mileage,car_type,cylinder,liter,doors,cruise,sound,leather):
|
125 |
+
input_data=pd.DataFrame({"Make":[make],
|
126 |
+
"Model":[model],
|
127 |
+
"Trim":[trim],
|
128 |
+
"Mileage":[mileage],
|
129 |
+
"Type":[car_type],
|
130 |
+
"Cylinder":[cylinder],
|
131 |
+
"Liter":[liter],
|
132 |
+
"Doors":[doors],
|
133 |
+
"Cruise":[cruise],
|
134 |
+
"Sound":[sound],
|
135 |
+
"Leather":[leather]})
|
136 |
+
prediction=pipe.predict(input_data)[0]
|
137 |
+
return prediction
|
138 |
+
st.title("Car Price Prediction:blue_car:@neslisahozturk")
|
139 |
+
st.write("Select the features of the car")
|
140 |
+
make=st.selectbox("Brand",df["Make"].unique())
|
141 |
+
model=st.selectbox("Model",df[df["Make"]==make]["Model"].unique())
|
142 |
+
trim=st.selectbox("Trim",df[(df["Make"]==make)&(df["Model"]==model)]["Trim"].unique())
|
143 |
+
mileage=st.number_input("Km",100,df["Mileage"].max())
|
144 |
+
car_type=st.selectbox("Car Type",df["Type"].unique())
|
145 |
+
cylinder=st.selectbox("Cylinder",df["Cylinder"].unique())
|
146 |
+
liter=st.number_input("Fuel Volume",df["Liter"].min(),df["Liter"].max())
|
147 |
+
doors=st.selectbox("Number of Doors",df["Doors"].unique())
|
148 |
+
cruise=st.radio("Velocity Constant",[True,False])
|
149 |
+
sound=st.radio("Sound System",[True,False])
|
150 |
+
leather=st.radio("Leather Seats",[True,False])
|
151 |
+
|
152 |
+
if st.button("Predict"):
|
153 |
+
pred=price(make,model,trim,mileage,car_type,cylinder,liter,doors,cruise,sound,leather)
|
154 |
+
st.write("Fiyat:$",round(pred[0],2))
|
155 |
+
|
156 |
+
|
157 |
+
# In[ ]:
|
158 |
+
|
159 |
+
|
160 |
+
|
161 |
+
|
cars.xls
ADDED
Binary file (142 kB). View file
|
|
requirements.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
streamlit==1.31.1
|
2 |
+
scikit-learn==1.4.1.post1
|
3 |
+
pandas==2.1.0
|
4 |
+
xlrd==2.0.1
|