Python Training Intensive
  • Workshops
  • Project Gallery
  • UQ Library Technology Training
Project-Python
                       Objective:  Identification of factors that determine selling price of houses in Melbourne

Composition of Sample:

Preliminary Analysis:

Price Rooms Distance Bedroom2 Bathroom Car BuildingArea
count 1.358000e+04 13580.000000 13580.000000 13580.000000 13580.000000 13518.000000 7130.000000
mean 1.075684e+06 2.937997 10.137776 2.914728 1.534242 1.610075 151.967650
std 6.393107e+05 0.955748 5.868725 0.965921 0.691712 0.962634 541.014538
min 8.500000e+04 1.000000 0.000000 0.000000 0.000000 0.000000 0.000000
25% 6.500000e+05 2.000000 6.100000 2.000000 1.000000 1.000000 93.000000
50% 9.030000e+05 3.000000 9.200000 3.000000 1.000000 2.000000 126.000000
75% 1.330000e+06 3.000000 13.000000 3.000000 2.000000 2.000000 174.000000
max 9.000000e+06 10.000000 48.100000 20.000000 8.000000 10.000000 44515.000000
Inference
OLS Regression Results
Dep. Variable: Price R-squared: 0.598
Model: OLS Adj. R-squared: 0.597
Method: Least Squares F-statistic: 584.8
Date: Fri, 13 Jun 2025 Prob (F-statistic): 0.00
Time: 11:28:23 Log-Likelihood: -1.0215e+05
No. Observations: 7101 AIC: 2.043e+05
Df Residuals: 7082 BIC: 2.045e+05
Df Model: 18
Covariance Type: nonrobust
coef std err t P>|t| [0.025 0.975]
Intercept 7.176e+05 3.46e+04 20.723 0.000 6.5e+05 7.85e+05
Type[T.t] -3.402e+05 1.81e+04 -18.798 0.000 -3.76e+05 -3.05e+05
Type[T.u] -5.058e+05 1.57e+04 -32.243 0.000 -5.37e+05 -4.75e+05
Method[T.S] 7.742e+04 1.6e+04 4.836 0.000 4.6e+04 1.09e+05
Method[T.SA] -4.084e+04 6.63e+04 -0.616 0.538 -1.71e+05 8.91e+04
Method[T.SP] 4.152e+04 2.01e+04 2.061 0.039 2035.151 8.1e+04
Method[T.VB] 2.653e+04 2.25e+04 1.180 0.238 -1.75e+04 7.06e+04
Regionname[T.EV] 4.513e+05 8.33e+04 5.415 0.000 2.88e+05 6.15e+05
Regionname[T.NM] -2.515e+05 2e+04 -12.583 0.000 -2.91e+05 -2.12e+05
Regionname[T.NV] 2.649e+05 8.72e+04 3.040 0.002 9.41e+04 4.36e+05
Regionname[T.SEM] 2.991e+05 3.51e+04 8.512 0.000 2.3e+05 3.68e+05
Regionname[T.SM] 2.657e+05 1.94e+04 13.726 0.000 2.28e+05 3.04e+05
Regionname[T.WM] -3.055e+05 2e+04 -15.268 0.000 -3.45e+05 -2.66e+05
Regionname[T.WV] 4.189e+04 9.69e+04 0.432 0.666 -1.48e+05 2.32e+05
Rooms 1.879e+05 8178.076 22.979 0.000 1.72e+05 2.04e+05
Bathroom 2.089e+05 9279.422 22.510 0.000 1.91e+05 2.27e+05
Distance -4.878e+04 1189.107 -41.018 0.000 -5.11e+04 -4.64e+04
Car 5.274e+04 6097.406 8.649 0.000 4.08e+04 6.47e+04
BuildingArea 41.3076 9.640 4.285 0.000 22.410 60.205
Omnibus: 5505.081 Durbin-Watson: 1.631
Prob(Omnibus): 0.000 Jarque-Bera (JB): 341887.549
Skew: 3.194 Prob(JB): 0.00
Kurtosis: 36.387 Cond. No. 1.11e+04


Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.11e+04. This might indicate that there are
strong multicollinearity or other numerical problems.
Conclusions:
Houses selling prices are dependent on 
                house type, selling type, no of rooms,
                no of bedrooms, no of bathrooms, 
                no of car parking slots, buildinf area,
                distance from UDB....