chnmayp/Pizza_Price_Prediction_Using_Machine_Learning

1
2import pandas as pd
3import numpy as np
4
5import pickle
6
7# df  = pd.read_csv('final_pizza.csv',index_col= 0)
8# df = df.drop(['time','date'], axis=1)
9
10
11
12# li = [357, 'hawaiian_m',1,'hawaiian','The Hawaiian Pizza','Classic','Sliced Ham, Pineapple, Mozzarella Cheese','M','Friday']
13# sample = np.array(li)
14# print(len(sample))
15
16class Pizza_Sales_Model():
17    @staticmethod
18    def give_prediction(sample):
19
20        li = []
21        
22        li.append(int(sample[0]))
23        # li.append(int(sample[1]))
24        li.append(int(sample[2]))
25        
26        f1 = open('pickle_files/pizza_id.pkl','rb')
27        l_enc1 = pickle.load(f1)
28        li.append((l_enc1.transform([sample[1]]))[0])
29        
30        
31        f2 = open('pickle_files/pizza_type_id.pkl','rb')
32        l_enc2 = pickle.load(f2)
33        li.append((l_enc2.transform([sample[3]]))[0])
34        
35        f3 = open('pickle_files/name.pkl','rb')
36        l_enc3 = pickle.load(f3)
37        li.append(l_enc3.transform([sample[4]])[0])
38        
39        f4 = open('pickle_files/category.pkl','rb')
40        l_enc4 = pickle.load(f4)
41        li.append(l_enc4.transform([sample[5]])[0])
42        
43        f5 = open('pickle_files/ingredients.pkl','rb')
44        l_enc5 = pickle.load(f5)
45        li.append((l_enc5.transform([sample[6]]))[0])
46        
47        f6 = open('pickle_files/size.pkl','rb')
48        l_enc6 = pickle.load(f6)
49        li.append(l_enc6.transform([sample[7]])[0])
50        
51        f7 = open('pickle_files/weekday.pkl','rb')
52        l_enc7 = pickle.load(f7)
53        li.append(l_enc7.transform([sample[8]])[0])
54        
55        encoded_sample = np.array([li])
56        encoded_sample
57        
58        model = pickle.load(open('pickle_files/modelRFR.pkl','rb'))
59        pred = model.predict(encoded_sample)
60        return pred