sai07/Tech-Price-Analyzer
0
1import streamlit as st2import pickle3import pandas as pd4import numpy as np5import requests6from streamlit_lottie import st_lottie7 8st.set_page_config(page_title="My Webpage",page_icon="🤵")9 10def load_lottieurl(url):11 r = requests.get(url)12 if r.status_code!=200:13 return None14 return r.json()15lottie_coding = load_lottieurl("https://lottie.host/c9e78571-886e-4a40-9285-d22e6422ee48/iXVZeU57Ej.json"16)17 18lottie_coding1 = load_lottieurl("https://lottie.host/e3101877-8ed2-4ea4-8780-d7835de800f4/cn3ZqmjzSD.json"19)20 21 22# for laptop we use the model is randomforest r2_score:-89%23def Laptop():24 pipe = pickle.load(open('pipe.pkl','rb'))25 26 df = pickle.load(open('df.pkl','rb'))27 28 st.title('Laptop Price Predictor')29 30 # brand31 company = st.selectbox("Brand",df['Company'].unique())32 33 # type of laptop34 type = st.selectbox("Type",df['TypeName'].unique())35 36 # ram37 ram = st.selectbox("RAM(in GB)",[2,4,6,8,12,16,24,32,64])38 39 # weight40 weight = st.number_input('Weight of the Laptop')41 42 # touchscreen43 touchscreen = st.selectbox("TouchScreen",['No','Yes'])44 45 # IPS46 ips = st.selectbox('IPS',['No','Yes'])47 48 # screen size49 screen_size = st.number_input("Screen Size")50 51 # resolution52 resolution = st.selectbox('Screen Resolution',['1920x1080','1366x768','1600x900','3840x2160','3200x1800','2880x1800','2560x1600','2560x1440','2304x1440'])53 54 #cpu55 cpu = st.selectbox('CPU',df['Cpu brand'].unique())56 57 hdd = st.selectbox('HDD(in GB)',[0,128,256,512,1024,2048])58 59 ssd = st.selectbox('SSD(in GB)',[0,8,128,256,512,1024])60 61 gpu = st.selectbox('GPU',df['Gpu brand'].unique())62 63 os = st.selectbox('OS',df['os'].unique())64 65 if st.button('Predict Price'):66 # query67 ppi = None68 if touchscreen == 'Yes':69 touchscreen = 170 else:71 touchscreen = 072 73 if ips == 'Yes':74 ips = 175 else:76 ips = 077 78 X_res = int(resolution.split('x')[0])79 Y_res = int(resolution.split('x')[1])80 ppi = ((X_res**2) + (Y_res**2))**0.5/screen_size81 query = np.array([company,type,ram,weight,touchscreen,ips,ppi,cpu,hdd,ssd,gpu,os])82 83 query = query.reshape(1,12)84 st.title("The predicted price of this configuration is " + str(int(np.exp(pipe.predict(query)[0]))))85 86 # st.markdown('<b><font color="orange" size="30">The predicted price of this configuration is: </font></b>', unsafe_allow_html=True)87 88 # st.title(str(int(np.exp(pipe.predict(query)[0]))))89 90 91def Mobile():92 pipe = pickle.load(open('pipe8.pkl','rb'))93 94 df = pickle.load(open('X_train.pkl','rb'))95 96 st.title('Mobile Price Predictor')97 98 # ['mobile_color', 'disp_size', 'os', 'num_cores', 'mp_speed',99 # 'int_memory', 'ram', 'battery_power', 'mob_width', 'mob_height',100 # 'mob_depth', 'mob_weight', 'res_dim_1', 'res_dim_2', 'p_cam_max',101 # 'p_cam_count', 'f_cam_max', 'f_cam_count', '2G', '3G', '4G', '4GVOLTE',102 # '5G']103 104 # mobile color105 color = st.selectbox("Color",df['mobile_color'].unique())106 107 # disp_size108 disp_size = st.number_input('Display Size(in inches)')109 110 # os111 os = st.selectbox("Operating System",sorted(df['os'].unique()))112 113 # num_cores114 num_cores = st.selectbox("No.of Cores",sorted(df['num_cores'].unique()))115 116 # speed of cpu117 mp_speed = disp_size = st.number_input('processor speed',help='2GHz processor')118 119 # memory120 int_memory = st.selectbox("Internal Memory",sorted(df['int_memory'].unique()))121 122 # ram123 ram = st.selectbox("RAM",sorted(df['ram'].unique(),reverse=True))124 125 # battery_power126 battery_power = st.selectbox("Battery",sorted(df['battery_power'].unique(),reverse=True))127 128 129 # mob_width130 mob_width = st.number_input('Mobile Width(mm)')131 132 # mob_height133 mob_height = st.number_input('Mobile Height(mm)')134 135 # mob_depth136 mob_depth = st.number_input('Mobile Depth(mm)')137 138 # mob_weight139 mob_weight = st.number_input('Mobile Weight')140 141 # resolution142 resolution = st.text_input("Enter Resulution")143 144 # p_cam_max145 p_cam_max = st.selectbox("Max rear camera",sorted(df['p_cam_max'].unique(),reverse=True),help='Primay Max camera')146 147 # p_cam_count148 p_cam_count = st.selectbox("Count of rear cameras",sorted(df['p_cam_count'].unique()))149 150 # f_cam_max151 f_cam_max = st.selectbox("Max front camera",sorted(df['f_cam_max'].unique()),help='Secondary Max camera')152 153 # f_cam_count154 f_cam_count = st.selectbox("Toatl no. of front cameras",[1,2],help='total no.of cameras including max camera')155 156 # Network157 network_choices = {158 "2G": df['2G'].unique(),159 "3G": df['3G'].unique(),160 "4G": df['4G'].unique(),161 "4GVOLTE": df['4GVOLTE'].unique(),162 "5G": df['5G'].unique()163 }164 165 selected_network = st.selectbox("Select Network", network_choices.keys())166 # selected_value = 1167 if selected_network == '2G':168 G2 = 1169 G3 = 0170 G4 = 0171 G4VOLTE = 0172 G5 = 0173 elif selected_network == '3G':174 G2 = 0175 G3 = 1176 G4 = 0177 G4VOLTE = 0178 G5 = 0179 elif selected_network == '4G':180 G2 = 0181 G3 = 0182 G4 = 1183 G4VOLTE = 0184 G5 = 0185 elif selected_network == '4GVOLTE':186 G2 = 0187 G3 = 0188 G4 = 0189 G4VOLTE = 1190 G5 = 0191 else:192 G2 = 0193 G3 = 0194 G4 = 0195 G4VOLTE = 0196 G5 = 1197 198 199 # 'mobile_color', 'dual_sim', 'disp_size', 'os', 'num_cores', 'mp_speed',200 # 'int_memory', 'ram', 'battery_power', 'mob_width', 'mob_height',201 # 'mob_depth', 'mob_weight', 'res_dim_1', 'res_dim_2', 'p_cam_max',202 # 'p_cam_count', 'f_cam_max', 'f_cam_count', '2G', '3G', '4G', '4GVOLTE',203 # '5G'204 if st.button('Predict Mobile Price'):205 res_dim_1 = int(resolution.split('x')[0])206 res_dim_2 = int(resolution.split('x')[1])207 208 209 query = np.array([color,disp_size,os,num_cores,mp_speed,int_memory,ram,battery_power,mob_width,mob_height,mob_depth,mob_weight,res_dim_1,res_dim_2,p_cam_max,p_cam_count,f_cam_max,f_cam_count,G2,G3,G4,G4VOLTE,G5])210 211 query = query.reshape(1,23)212 213 st.title("The predicted price of this configuration is " + str(int(pipe.predict(query)[0])))214 215# pip install pandas==1.5.3216 217 218 219# Define two buttons with unique keys220with st.container():221 left,right = st.columns(2)222 with left:223 button_clicked1 = st.button("Click For Mobile Price Predictor!📱", key="button1")224 st_lottie(lottie_coding1,height=200,key='Laptop')225 button_clicked2 = st.button("Click For Laptop Price Predictor!💻", key="button2")226 with right:227 st_lottie(lottie_coding,height=200,key='Mobile')228 229 230 231# Use a session state to track whether each button has been clicked232if 'button1_click_state' not in st.session_state:233 st.session_state.button1_click_state = False234 235if 'button2_click_state' not in st.session_state:236 st.session_state.button2_click_state = False237 238# Check if each button was clicked239if button_clicked1:240 st.session_state.button1_click_state = True241 st.session_state.button2_click_state = False242 243if button_clicked2:244 st.session_state.button2_click_state = True245 st.session_state.button1_click_state = False246 247# Display content based on button clicks248if st.session_state.button1_click_state:249 # Clear previous content250 st.empty()251 # Display con252 # tent for the first button253 Mobile()254 255if st.session_state.button2_click_state:256 # Clear previous content257 st.empty()258 # Display content for the second button259 Laptop()260 261