In [204]:
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import mpl_toolkits
import numpy as np
import scipy.stats as stats
%matplotlib inline
from sklearn.model_selection import train_test_split
In [220]:
df=pd.read_csv(r"C:\Users\Ismail\Desktop\RealEstateAU_1000_Samples.csv",skipinitialspace = True)
In [227]:
df
Out[227]:
| index | TID | breadcrumb | category_name | property_type | building_size | land_size | preferred_size | open_date | listing_agency | ... | state | zip_code | phone | latitude | longitude | product_depth | bedroom_count | bathroom_count | parking_count | RunDate | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 1350988 | Buy>NT>DARWIN CITY | Real Estate & Property for sale in DARWIN CITY... | House | NaN | NaN | NaN | Added 2 hours ago | Professionals - DARWIN CITY | ... | NT | 800 | 08 8941 8289 | NaN | NaN | premiere | 2.0 | 1.0 | 1.0 | 2022-05-27 15:54:05 |
| 1 | 1 | 1350989 | Buy>NT>DARWIN CITY | Real Estate & Property for sale in DARWIN CITY... | Apartment | 171m² | NaN | 171m² | Added 7 hours ago | Nick Mousellis Real Estate - Eview Group Member | ... | NT | 800 | 0411724000 | NaN | NaN | premiere | 3.0 | 2.0 | 2.0 | 2022-05-27 15:54:05 |
| 2 | 2 | 1350990 | Buy>NT>DARWIN CITY | Real Estate & Property for sale in DARWIN CITY... | Unit | NaN | NaN | NaN | Added 22 hours ago | Habitat Real Estate - THE GARDENS | ... | NT | 800 | 08 8981 0080 | NaN | NaN | premiere | 2.0 | 1.0 | 1.0 | 2022-05-27 15:54:05 |
| 3 | 3 | 1350991 | Buy>NT>DARWIN CITY | Real Estate & Property for sale in DARWIN CITY... | House | NaN | NaN | NaN | Added yesterday | Ray White - NIGHTCLIFF | ... | NT | 800 | 08 8982 2403 | NaN | NaN | premiere | 1.0 | 1.0 | 0.0 | 2022-05-27 15:54:05 |
| 4 | 4 | 1350992 | Buy>NT>DARWIN CITY | Real Estate & Property for sale in DARWIN CITY... | Unit | 201m² | NaN | 201m² | Added yesterday | Carol Need Real Estate - Fannie Bay | ... | NT | 800 | 0418885966 | NaN | NaN | premiere | 3.0 | 2.0 | 2.0 | 2022-05-27 15:54:05 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 995 | 995 | 1351983 | Buy>NT>DARWIN | Real Estate & Property for sale in DARWIN, NT ... | House | NaN | 9.17ha | 9.17ha | Under offer | United Realty NT - Parap | ... | NT | 834 | 08 8981 2666 | NaN | NaN | feature | 4.0 | 3.0 | 6.0 | 2022-05-27 15:54:05 |
| 996 | 996 | 1351984 | Buy>NT>DARWIN | Real Estate & Property for sale in DARWIN, NT ... | House | 203m² | 600m² | 600m² | NaN | Kassiou Constructions - HOWARD SPRINGS | ... | NT | 836 | 08 89834326 | NaN | NaN | standard | 4.0 | 2.0 | 2.0 | 2022-05-27 15:54:05 |
| 997 | 997 | 1351985 | Buy>NT>DARWIN | Real Estate & Property for sale in DARWIN, NT ... | House | 209.6m² | 800m² | 800m² | NaN | Kassiou Constructions - HOWARD SPRINGS | ... | NT | 836 | 08 89834326 | NaN | NaN | standard | 4.0 | 2.0 | 2.0 | 2022-05-27 15:54:05 |
| 998 | 998 | 1351986 | Buy>NT>DARWIN | Real Estate & Property for sale in DARWIN, NT ... | House | 180m² | 450m² | 450m² | NaN | Kassiou Constructions - HOWARD SPRINGS | ... | NT | 810 | 08 89834326 | NaN | NaN | standard | 4.0 | 2.0 | 3.0 | 2022-05-27 15:54:05 |
| 999 | 999 | 1351987 | Buy>NT>DARWIN | Real Estate & Property for sale in DARWIN, NT ... | Unit | 120m² | NaN | 120m² | NaN | Home Zone NT - DARWIN | ... | NT | 820 | 0418 895 345 | NaN | NaN | feature | 2.0 | 2.0 | 2.0 | 2022-05-27 15:54:05 |
1000 rows × 27 columns
In [228]:
df.head
Out[228]:
<bound method NDFrame.head of index TID breadcrumb \
0 0 1350988 Buy>NT>DARWIN CITY
1 1 1350989 Buy>NT>DARWIN CITY
2 2 1350990 Buy>NT>DARWIN CITY
3 3 1350991 Buy>NT>DARWIN CITY
4 4 1350992 Buy>NT>DARWIN CITY
.. ... ... ...
995 995 1351983 Buy>NT>DARWIN
996 996 1351984 Buy>NT>DARWIN
997 997 1351985 Buy>NT>DARWIN
998 998 1351986 Buy>NT>DARWIN
999 999 1351987 Buy>NT>DARWIN
category_name property_type \
0 Real Estate & Property for sale in DARWIN CITY... House
1 Real Estate & Property for sale in DARWIN CITY... Apartment
2 Real Estate & Property for sale in DARWIN CITY... Unit
3 Real Estate & Property for sale in DARWIN CITY... House
4 Real Estate & Property for sale in DARWIN CITY... Unit
.. ... ...
995 Real Estate & Property for sale in DARWIN, NT ... House
996 Real Estate & Property for sale in DARWIN, NT ... House
997 Real Estate & Property for sale in DARWIN, NT ... House
998 Real Estate & Property for sale in DARWIN, NT ... House
999 Real Estate & Property for sale in DARWIN, NT ... Unit
building_size land_size preferred_size open_date \
0 NaN NaN NaN Added 2 hours ago
1 171m² NaN 171m² Added 7 hours ago
2 NaN NaN NaN Added 22 hours ago
3 NaN NaN NaN Added yesterday
4 201m² NaN 201m² Added yesterday
.. ... ... ... ...
995 NaN 9.17ha 9.17ha Under offer
996 203m² 600m² 600m² NaN
997 209.6m² 800m² 800m² NaN
998 180m² 450m² 450m² NaN
999 120m² NaN 120m² NaN
listing_agency ... state zip_code \
0 Professionals - DARWIN CITY ... NT 800
1 Nick Mousellis Real Estate - Eview Group Member ... NT 800
2 Habitat Real Estate - THE GARDENS ... NT 800
3 Ray White - NIGHTCLIFF ... NT 800
4 Carol Need Real Estate - Fannie Bay ... NT 800
.. ... ... ... ...
995 United Realty NT - Parap ... NT 834
996 Kassiou Constructions - HOWARD SPRINGS ... NT 836
997 Kassiou Constructions - HOWARD SPRINGS ... NT 836
998 Kassiou Constructions - HOWARD SPRINGS ... NT 810
999 Home Zone NT - DARWIN ... NT 820
phone latitude longitude product_depth bedroom_count \
0 08 8941 8289 NaN NaN premiere 2.0
1 0411724000 NaN NaN premiere 3.0
2 08 8981 0080 NaN NaN premiere 2.0
3 08 8982 2403 NaN NaN premiere 1.0
4 0418885966 NaN NaN premiere 3.0
.. ... ... ... ... ...
995 08 8981 2666 NaN NaN feature 4.0
996 08 89834326 NaN NaN standard 4.0
997 08 89834326 NaN NaN standard 4.0
998 08 89834326 NaN NaN standard 4.0
999 0418 895 345 NaN NaN feature 2.0
bathroom_count parking_count RunDate
0 1.0 1.0 2022-05-27 15:54:05
1 2.0 2.0 2022-05-27 15:54:05
2 1.0 1.0 2022-05-27 15:54:05
3 1.0 0.0 2022-05-27 15:54:05
4 2.0 2.0 2022-05-27 15:54:05
.. ... ... ...
995 3.0 6.0 2022-05-27 15:54:05
996 2.0 2.0 2022-05-27 15:54:05
997 2.0 2.0 2022-05-27 15:54:05
998 2.0 3.0 2022-05-27 15:54:05
999 2.0 2.0 2022-05-27 15:54:05
[1000 rows x 27 columns]>
In [229]:
df.dropna
Out[229]:
<bound method DataFrame.dropna of index TID breadcrumb \
0 0 1350988 Buy>NT>DARWIN CITY
1 1 1350989 Buy>NT>DARWIN CITY
2 2 1350990 Buy>NT>DARWIN CITY
3 3 1350991 Buy>NT>DARWIN CITY
4 4 1350992 Buy>NT>DARWIN CITY
.. ... ... ...
995 995 1351983 Buy>NT>DARWIN
996 996 1351984 Buy>NT>DARWIN
997 997 1351985 Buy>NT>DARWIN
998 998 1351986 Buy>NT>DARWIN
999 999 1351987 Buy>NT>DARWIN
category_name property_type \
0 Real Estate & Property for sale in DARWIN CITY... House
1 Real Estate & Property for sale in DARWIN CITY... Apartment
2 Real Estate & Property for sale in DARWIN CITY... Unit
3 Real Estate & Property for sale in DARWIN CITY... House
4 Real Estate & Property for sale in DARWIN CITY... Unit
.. ... ...
995 Real Estate & Property for sale in DARWIN, NT ... House
996 Real Estate & Property for sale in DARWIN, NT ... House
997 Real Estate & Property for sale in DARWIN, NT ... House
998 Real Estate & Property for sale in DARWIN, NT ... House
999 Real Estate & Property for sale in DARWIN, NT ... Unit
building_size land_size preferred_size open_date \
0 NaN NaN NaN Added 2 hours ago
1 171m² NaN 171m² Added 7 hours ago
2 NaN NaN NaN Added 22 hours ago
3 NaN NaN NaN Added yesterday
4 201m² NaN 201m² Added yesterday
.. ... ... ... ...
995 NaN 9.17ha 9.17ha Under offer
996 203m² 600m² 600m² NaN
997 209.6m² 800m² 800m² NaN
998 180m² 450m² 450m² NaN
999 120m² NaN 120m² NaN
listing_agency ... state zip_code \
0 Professionals - DARWIN CITY ... NT 800
1 Nick Mousellis Real Estate - Eview Group Member ... NT 800
2 Habitat Real Estate - THE GARDENS ... NT 800
3 Ray White - NIGHTCLIFF ... NT 800
4 Carol Need Real Estate - Fannie Bay ... NT 800
.. ... ... ... ...
995 United Realty NT - Parap ... NT 834
996 Kassiou Constructions - HOWARD SPRINGS ... NT 836
997 Kassiou Constructions - HOWARD SPRINGS ... NT 836
998 Kassiou Constructions - HOWARD SPRINGS ... NT 810
999 Home Zone NT - DARWIN ... NT 820
phone latitude longitude product_depth bedroom_count \
0 08 8941 8289 NaN NaN premiere 2.0
1 0411724000 NaN NaN premiere 3.0
2 08 8981 0080 NaN NaN premiere 2.0
3 08 8982 2403 NaN NaN premiere 1.0
4 0418885966 NaN NaN premiere 3.0
.. ... ... ... ... ...
995 08 8981 2666 NaN NaN feature 4.0
996 08 89834326 NaN NaN standard 4.0
997 08 89834326 NaN NaN standard 4.0
998 08 89834326 NaN NaN standard 4.0
999 0418 895 345 NaN NaN feature 2.0
bathroom_count parking_count RunDate
0 1.0 1.0 2022-05-27 15:54:05
1 2.0 2.0 2022-05-27 15:54:05
2 1.0 1.0 2022-05-27 15:54:05
3 1.0 0.0 2022-05-27 15:54:05
4 2.0 2.0 2022-05-27 15:54:05
.. ... ... ...
995 3.0 6.0 2022-05-27 15:54:05
996 2.0 2.0 2022-05-27 15:54:05
997 2.0 2.0 2022-05-27 15:54:05
998 2.0 3.0 2022-05-27 15:54:05
999 2.0 2.0 2022-05-27 15:54:05
[1000 rows x 27 columns]>
In [230]:
print(df.columns)
Index(['index', 'TID', 'breadcrumb', 'category_name', 'property_type',
'building_size', 'land_size', 'preferred_size', 'open_date',
'listing_agency', 'price', 'location_number', 'location_type',
'location_name', 'address', 'address_1', 'city', 'state', 'zip_code',
'phone', 'latitude', 'longitude', 'product_depth', 'bedroom_count',
'bathroom_count', 'parking_count', 'RunDate'],
dtype='object')
In [231]:
n_df = df[['building_size','bedroom_count','bathroom_count', 'parking_count','price']]
In [232]:
df_n = n_df.fillna(0)
In [233]:
df_n
Out[233]:
| building_size | bedroom_count | bathroom_count | parking_count | price | |
|---|---|---|---|---|---|
| 0 | 0 | 2.0 | 1.0 | 1.0 | $435,000 |
| 1 | 171m² | 3.0 | 2.0 | 2.0 | Offers Over $320,000 |
| 2 | 0 | 2.0 | 1.0 | 1.0 | $310,000 |
| 3 | 0 | 1.0 | 1.0 | 0.0 | $259,000 |
| 4 | 201m² | 3.0 | 2.0 | 2.0 | $439,000 |
| ... | ... | ... | ... | ... | ... |
| 995 | 0 | 4.0 | 3.0 | 6.0 | 2 Residence |
| 996 | 203m² | 4.0 | 2.0 | 2.0 | $601,000 |
| 997 | 209.6m² | 4.0 | 2.0 | 2.0 | $655,000 |
| 998 | 180m² | 4.0 | 2.0 | 3.0 | $675,000 |
| 999 | 120m² | 2.0 | 2.0 | 2.0 | $399,000 |
1000 rows × 5 columns
In [234]:
df_n['bedroom_count'].value_counts().plot(kind='bar')
plt.title('number of Bedroom')
plt.xlabel('Bedrooms')
plt.ylabel('Count')
sns.despine
Out[234]:
<function seaborn.utils.despine(fig=None, ax=None, top=True, right=True, left=False, bottom=False, offset=None, trim=False)>
In [235]:
df_n['parking_count'].value_counts().plot(kind='bar')
plt.title('parking_count')
plt.xlabel('Parking')
plt.ylabel('Count')
sns.despine
Out[235]:
<function seaborn.utils.despine(fig=None, ax=None, top=True, right=True, left=False, bottom=False, offset=None, trim=False)>
In [236]:
plt.scatter(df.bedroom_count,df_n.price)
plt.title("Bedroom and Price ")
plt.xlabel("Bedrooms")
plt.ylabel("Price")
plt.show()
sns.despine
Out[236]:
<function seaborn.utils.despine(fig=None, ax=None, top=True, right=True, left=False, bottom=False, offset=None, trim=False)>
In [237]:
df_p = df_n.price
df_p
Out[237]:
0 $435,000
1 Offers Over $320,000
2 $310,000
3 $259,000
4 $439,000
...
995 2 Residence
996 $601,000
997 $655,000
998 $675,000
999 $399,000
Name: price, Length: 1000, dtype: object
In [238]:
df_p.map(lambda x: x.lstrip('$'))
Out[238]:
0 435,000
1 Offers Over $320,000
2 310,000
3 259,000
4 439,000
...
995 2 Residence
996 601,000
997 655,000
998 675,000
999 399,000
Name: price, Length: 1000, dtype: object
In [239]:
import re
df_p = df_p.apply(lambda row: re.sub("[^0-9]"," ", row))
In [240]:
df_p
Out[240]:
0 435 000
1 320 000
2 310 000
3 259 000
4 439 000
...
995 2
996 601 000
997 655 000
998 675 000
999 399 000
Name: price, Length: 1000, dtype: object
In [241]:
from sklearn.linear_model import LinearRegression
In [242]:
X=df_n[['bedroom_count','bathroom_count', 'parking_count']]
y=df_p
In [243]:
X
Out[243]:
| bedroom_count | bathroom_count | parking_count | |
|---|---|---|---|
| 0 | 2.0 | 1.0 | 1.0 |
| 1 | 3.0 | 2.0 | 2.0 |
| 2 | 2.0 | 1.0 | 1.0 |
| 3 | 1.0 | 1.0 | 0.0 |
| 4 | 3.0 | 2.0 | 2.0 |
| ... | ... | ... | ... |
| 995 | 4.0 | 3.0 | 6.0 |
| 996 | 4.0 | 2.0 | 2.0 |
| 997 | 4.0 | 2.0 | 2.0 |
| 998 | 4.0 | 2.0 | 3.0 |
| 999 | 2.0 | 2.0 | 2.0 |
1000 rows × 3 columns
In [244]:
y
Out[244]:
0 435 000
1 320 000
2 310 000
3 259 000
4 439 000
...
995 2
996 601 000
997 655 000
998 675 000
999 399 000
Name: price, Length: 1000, dtype: object
In [245]:
from sklearn.model_selection import train_test_split
In [246]:
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=2)
In [247]:
X_train
Out[247]:
| bedroom_count | bathroom_count | parking_count | |
|---|---|---|---|
| 175 | 1.0 | 1.0 | 2.0 |
| 818 | 3.0 | 2.0 | 2.0 |
| 677 | 4.0 | 2.0 | 2.0 |
| 952 | 1.0 | 1.0 | 1.0 |
| 200 | 3.0 | 1.0 | 3.0 |
| ... | ... | ... | ... |
| 534 | 6.0 | 2.0 | 6.0 |
| 584 | 3.0 | 1.0 | 2.0 |
| 493 | 3.0 | 1.0 | 1.0 |
| 527 | 4.0 | 2.0 | 2.0 |
| 168 | 3.0 | 2.0 | 2.0 |
800 rows × 3 columns
In [248]:
len(X_train)
Out[248]:
800
In [249]:
X_test
Out[249]:
| bedroom_count | bathroom_count | parking_count | |
|---|---|---|---|
| 37 | 1.0 | 1.0 | 1.0 |
| 726 | 4.0 | 2.0 | 2.0 |
| 846 | 4.0 | 2.0 | 4.0 |
| 295 | 3.0 | 1.0 | 4.0 |
| 924 | 2.0 | 2.0 | 2.0 |
| ... | ... | ... | ... |
| 839 | 1.0 | 1.0 | 0.0 |
| 810 | 3.0 | 1.0 | 2.0 |
| 930 | 3.0 | 2.0 | 2.0 |
| 616 | 4.0 | 2.0 | 2.0 |
| 809 | 3.0 | 1.0 | 2.0 |
200 rows × 3 columns
In [250]:
len(X_test)
Out[250]:
200
In [251]:
y_test
Out[251]:
37 465 000
726 750 000
846
295 629 000
924
...
839
810 462 500
930 515 000
616 559 000
809 375 000
Name: price, Length: 200, dtype: object
In [252]:
y_train
Out[252]:
175 399 000
818 865 000
677 639 000
952 235 000
200 419 000
...
534
584 375 000
493 395 000
527
168 480 000
Name: price, Length: 800, dtype: object
In [253]:
clf = LinearRegression()
In [ ]:
clf.fit(X_train,y_train)
In [ ]:
clf.predict(X_test)
In [ ]:
clf.score(X_test,y_test)