Spaces:
Build error
Build error
File size: 4,699 Bytes
cf5dd5c 3969c17 cf5dd5c aa7428d 2726493 aa7428d cf5dd5c d1ed6db cf5dd5c aa7428d cf5dd5c aa7428d 7560521 cf5dd5c aa7428d cf5dd5c 7bb60c9 aa7428d 7560521 aa7428d 7560521 aa7428d cf5dd5c 3969c17 aa7428d |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 |
import pandas as pd
import streamlit as st
import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import r2_score
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
import seaborn as sns
# loading the data
df = pd.read_csv('train2.csv')
# Renaming columns
#df.rename(columns = {'MSSubClass':'import pandas as pd
import streamlit as st
import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import r2_score
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
import seaborn as sns
# loading the data
df = pd.read_csv('train2.csv')
# Renaming columns
df.rename(columns = {'MSSubClass':'MSSubClass','LotArea':'LotArea', 'OverallQual':'OverallQual','OverallCond':'OverallCond', 'YearBuilt':'YearBuilt',
'MasVnrArea':'MasVnrArea', 'BsmtFinSF1':'BsmtFinSF1', 'BsmtFinSF2':'BsmtFinSF2',
'BsmtUnfSF':'BsmtUnfSF','TotalBsmtSF':'TotalBsmtSF'},inplace = True)
# HEADINGS
st.title('House Price Prediction')
st.sidebar.header('Housing Data')
st.subheader('Training Data Stats')
st.write(df.describe())
# X AND Y DATA
x = df.drop(['SalePrice'], axis = 1)
y = df.iloc[:, -1]
x_train, x_test, y_train, y_test = train_test_split(x,y, test_size = 0.2, random_state = 0)
# FUNCTION
def user_report():
MSSubClass = st.sidebar.slider('MSSubClass', 17795,107702, 18000 )
LotArea = st.sidebar.slider('LotArea', 2,10, 4 )
OverallQual = st.sidebar.slider('OverallQual', 3,11, 5 )
OverallCond = st.sidebar.slider('OverallCond', 2,7, 3 )
YearBuilt = st.sidebar.slider('YearBuilt', 170,70000, 5000 )
MasVnrArea = st.sidebar.slider('MasVnrArea', 170,70000, 5000 )
BsmtFinSF1 = st.sidebar.slider('BsmtFinSF1', 170,70000, 5000 )
BsmtUnfSF = st.sidebar.slider('BsmtUnfSF', 170,70000, 5000 )
BsmtFinSF2 = st.sidebar.slider('BsmtFinSF2', 170,70000, 5000 )
TotalBsmtSF = st.sidebar.slider('TotalBsmtSF', 170,70000, 5000 )
user_report_data = {
'MSSubClass':MSSubClass,
'LotArea':LotArea,
'OverallQual':OverallQual,
'YearBuilt':YearBuilt,
'MasVnrArea':MasVnrArea,
'BsmtFinSF1': BsmtFinSF1,
'BsmtFinSF': BsmtFinSF,
'BsmtFinSF2': BsmtFinSF2,
'TotalBsmtSF': TotalBsmtSF,
}
report_data = pd.DataFrame(user_report_data, index=[0])
return report_data
# Housing Data
user_data = user_report()
st.subheader('Housing Data')
st.write(user_data)
# MODEL
lr = LinearRegression()
lr.fit(x_train, y_train)
user_result = lr.predict(user_data)
# VISUALISATIONS
st.title('Visualised Housing Data')
# COLOR FUNCTION
if user_result[0]==0:
color = 'blue'
else:
color = 'red'
# OUTPUT
st.subheader('Price of House is : ')
st.write(str(user_result))
st.title('output')
st.subheader('r2_score: ')
st.write(str(r2_score(y_test, lr.predict(x_test))*100)+'%')
# HEADINGS
st.title('House Price Prediction')
st.sidebar.header('Housing Data')
st.subheader('Training Data Stats')
st.write(df.describe())
# X AND Y DATA
x = df.drop(['SalePrice'], axis = 1)
y = df.iloc[:, -1]
x_train, x_test, y_train, y_test = train_test_split(x,y, test_size = 0.2, random_state = 0)
# FUNCTION
def user_report():
MSSubClass = st.sidebar.slider('MSSubClass', 17795,107702, 18000 )
LotArea = st.sidebar.slider('LotArea', 2,10, 4 )
OverallQual = st.sidebar.slider('OverallQual', 3,11, 5 )
OverallCond = st.sidebar.slider('OverallCond', 2,7, 3 )
YearBuilt = st.sidebar.slider('YearBuilt', 170,70000, 5000 )
MasVnrArea = st.sidebar.slider('MasVnrArea', 170,70000, 5000 )
BsmtFinSF1 = st.sidebar.slider('BsmtFinSF1', 170,70000, 5000 )
BsmtUnfSF = st.sidebar.slider('BsmtUnfSF', 170,70000, 5000 )
BsmtFinSF2 = st.sidebar.slider('BsmtFinSF2', 170,70000, 5000 )
TotalBsmtSF = st.sidebar.slider('TotalBsmtSF', 170,70000, 5000 )
user_report_data = {
'MSSubClass':MSSubClass,
'LotArea':LotArea,
'OverallQual':OverallQual,
'YearBuilt':YearBuilt,
'MasVnrArea':MasVnrArea,
'BsmtFinSF1': BsmtFinSF1,
'BsmtFinSF': BsmtFinSF,
'BsmtFinSF2': BsmtFinSF2,
'TotalBsmtSF': TotalBsmtSF,
}
report_data = pd.DataFrame(user_report_data, index=[0])
return report_data
# Housing Data
user_data = user_report()
st.subheader('Housing Data')
st.write(user_data)
# MODEL
lr = LinearRegression()
lr.fit(x_train, y_train)
user_result = lr.predict(user_data)
# VISUALISATIONS
st.title('Visualised Housing Data')
# COLOR FUNCTION
if user_result[0]==0:
color = 'blue'
else:
color = 'red'
# OUTPUT
st.subheader('Price of House is : ')
st.write(str(user_result))
st.title('output')
st.subheader('r2_score: ')
st.write(str(r2_score(y_test, lr.predict(x_test))*100)+'%')
|