22 KiB
22 KiB
Download data:
run commands:
- pip install --user kaggle #API Kaggle, do pobrania zbioru
- pip install --user pandas
- kaggle datasets download -d akash14/house-price-dataset (U have to have Kaggle token, more info here: https://www.kaggle.com/docs/api)
- unzip -o house-price-dataset.zip / tar -xf .\house-price-dataset.zip (for windows)
data from https://www.kaggle.com/datasets/akash14/house-price-dataset
import pandas as pd
# paths
filePathTest = "../Participants_Data_HPP/Train.csv"
filePathTrain = "../Participants_Data_HPP/Test.csv"
dataTest = pd.read_csv(filePathTest)
dataTrain = pd.read_csv(filePathTrain)
number_lines = len(dataTest.index)
row_size = number_lines // 2
# start looping through data writing it to a new file for each set
# no of csv files with row size
k = 2
size = row_size
# split test data to test and dev
for i in range(k):
df = dataTest[size * i:size * (i + 1)]
name = ""
if i == 0:
name = "Dev"
else:
name = "Test"
df.to_csv(f'../Participants_Data_HPP/' + name + '.csv', index=False)
df_1 = pd.read_csv("../Participants_Data_HPP/Dev.csv")
df_2 = pd.read_csv("../Participants_Data_HPP/Test.csv")
df_3 = pd.read_csv("../Participants_Data_HPP/Train.csv")
print("dev:" + str(len(df_1)))
print("test:" + str(len(df_2)))
print("train:" + str(len(df_3)))
dev:14725 test:14725 train:29451
import pandas as pd
import matplotlib.pyplot as plt
#https://www.kaggle.com/code/aadhavvignesh/regression-with-scikit-learn-practical-ml-1
dataPath = '../Participants_Data_HPP/Train.csv'
#data informations
data = pd.read_csv(dataPath)info = data.info()<class 'pandas.core.frame.DataFrame'> RangeIndex: 29451 entries, 0 to 29450 Data columns (total 12 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 POSTED_BY 29451 non-null object 1 UNDER_CONSTRUCTION 29451 non-null int64 2 RERA 29451 non-null int64 3 BHK_NO. 29451 non-null int64 4 BHK_OR_RK 29451 non-null object 5 SQUARE_FT 29451 non-null float64 6 READY_TO_MOVE 29451 non-null int64 7 RESALE 29451 non-null int64 8 ADDRESS 29451 non-null object 9 LONGITUDE 29451 non-null float64 10 LATITUDE 29451 non-null float64 11 TARGET(PRICE_IN_LACS) 29451 non-null float64 dtypes: float64(4), int64(5), object(3) memory usage: 2.7+ MB
description = data.describe(include="all")
print(description) POSTED_BY UNDER_CONSTRUCTION RERA BHK_NO. BHK_OR_RK \
count 29451 29451.000000 29451.000000 29451.000000 29451
unique 3 NaN NaN NaN 2
top Dealer NaN NaN NaN BHK
freq 18291 NaN NaN NaN 29427
mean NaN 0.179756 0.317918 2.392279 NaN
std NaN 0.383991 0.465675 0.879091 NaN
min NaN 0.000000 0.000000 1.000000 NaN
25% NaN 0.000000 0.000000 2.000000 NaN
50% NaN 0.000000 0.000000 2.000000 NaN
75% NaN 0.000000 1.000000 3.000000 NaN
max NaN 1.000000 1.000000 20.000000 NaN
SQUARE_FT READY_TO_MOVE RESALE ADDRESS \
count 2.945100e+04 29451.000000 29451.000000 29451
unique NaN NaN NaN 6899
top NaN NaN NaN Zirakpur,Chandigarh
freq NaN NaN NaN 509
mean 1.980217e+04 0.820244 0.929578 NaN
std 1.901335e+06 0.383991 0.255861 NaN
min 3.000000e+00 0.000000 0.000000 NaN
25% 9.000211e+02 1.000000 1.000000 NaN
50% 1.175057e+03 1.000000 1.000000 NaN
75% 1.550688e+03 1.000000 1.000000 NaN
max 2.545455e+08 1.000000 1.000000 NaN
LONGITUDE LATITUDE TARGET(PRICE_IN_LACS)
count 29451.000000 29451.000000 29451.000000
unique NaN NaN NaN
top NaN NaN NaN
freq NaN NaN NaN
mean 21.300255 76.837695 142.898746
std 6.205306 10.557747 656.880713
min -37.713008 -121.761248 0.250000
25% 18.452663 73.798100 38.000000
50% 20.750000 77.324137 62.000000
75% 26.900926 77.828740 100.000000
max 59.912884 152.962676 30000.000000
corr = data.corr()
print(corr) UNDER_CONSTRUCTION RERA BHK_NO. SQUARE_FT \
UNDER_CONSTRUCTION 1.000000 0.363826 -0.040712 -0.004204
RERA 0.363826 1.000000 0.009547 -0.006229
BHK_NO. -0.040712 0.009547 1.000000 0.005303
SQUARE_FT -0.004204 -0.006229 0.005303 1.000000
READY_TO_MOVE -1.000000 -0.363826 0.040712 0.004204
RESALE -0.347405 -0.270351 0.014581 0.001732
LONGITUDE 0.006440 0.104976 0.068730 -0.012591
LATITUDE -0.000381 -0.065106 0.046930 0.000803
TARGET(PRICE_IN_LACS) 0.055399 0.067636 0.112283 0.402685
READY_TO_MOVE RESALE LONGITUDE LATITUDE \
UNDER_CONSTRUCTION -1.000000 -0.347405 0.006440 -0.000381
RERA -0.363826 -0.270351 0.104976 -0.065106
BHK_NO. 0.040712 0.014581 0.068730 0.046930
SQUARE_FT 0.004204 0.001732 -0.012591 0.000803
READY_TO_MOVE 1.000000 0.347405 -0.006440 0.000381
RESALE 0.347405 1.000000 0.024038 0.014844
LONGITUDE -0.006440 0.024038 1.000000 -0.155062
LATITUDE 0.000381 0.014844 -0.155062 1.000000
TARGET(PRICE_IN_LACS) -0.055399 -0.207378 -0.031112 -0.017254
TARGET(PRICE_IN_LACS)
UNDER_CONSTRUCTION 0.055399
RERA 0.067636
BHK_NO. 0.112283
SQUARE_FT 0.402685
READY_TO_MOVE -0.055399
RESALE -0.207378
LONGITUDE -0.031112
LATITUDE -0.017254
TARGET(PRICE_IN_LACS) 1.000000
#print(data.head())
data["BHK_NO."].value_counts().plot(kind="bar")<AxesSubplot:>
#select the most significant
data = data[['TARGET(PRICE_IN_LACS)', 'SQUARE_FT', 'BHK_NO.', 'RESALE']]
#normalize price column and flat area using min max technique
columnName1 = 'TARGET(PRICE_IN_LACS)'
columnName2 = 'SQUARE_FT'
column1Min = data[columnName1].min()
column1Max = data[columnName1].max()
column2Min = data[columnName2].min()
column2Max = data[columnName2].max()
data[columnName1] = (data[columnName1] - column1Min) / (column1Max - column1Min)
data[columnName2] = (data[columnName2] - column2Min) / (column2Max - column2Min)
data.describe(include="all")| TARGET(PRICE_IN_LACS) | SQUARE_FT | BHK_NO. | RESALE | |
|---|---|---|---|---|
| count | 29451.000000 | 29451.000000 | 29451.000000 | 29451.000000 |
| mean | 0.004755 | 0.000078 | 2.392279 | 0.929578 |
| std | 0.021896 | 0.007470 | 0.879091 | 0.255861 |
| min | 0.000000 | 0.000000 | 1.000000 | 0.000000 |
| 25% | 0.001258 | 0.000004 | 2.000000 | 1.000000 |
| 50% | 0.002058 | 0.000005 | 2.000000 | 1.000000 |
| 75% | 0.003325 | 0.000006 | 3.000000 | 1.000000 |
| max | 1.000000 | 1.000000 | 20.000000 | 1.000000 |