1
0
forked from tdwojak/Python2018
This commit is contained in:
wagner.agnieszka 2018-06-23 01:00:53 +02:00
parent 49fe26305c
commit 325549ab4a
3 changed files with 114 additions and 2 deletions

56
labs06/linearModel.py Normal file
View File

@ -0,0 +1,56 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import sklearn
import pandas as pd
import numpy as np
dane = pd.read_csv("mieszkania.csv")
print(dane.head())
print(dane.columns)
# check data for outliers
from matplotlib import pyplot as plt
plt.scatter(dane['SqrMeters'], dane['Expected'], color='g')
plt.show()
# remove all data points that have expected price <= 500.000 and living area <= 200 sqrt meters
plt.scatter(dane['Rooms'], dane['Expected'], color='g')
plt.show()
# remove all data points that represent flats with more than 8 rooms
flats = dane[(dane['Rooms'] < 10) & (dane['SqrMeters'] <= 200) & (dane['Expected'] <= 500000)]
print(flats.head(20))
y = flats['Expected']
X = flats.drop(['Id', 'Expected', 'Floor', 'Location',
'Description', 'Unnamed: 7', 'Unnamed: 8', 'Unnamed: 9', 'Unnamed: 10', 'Unnamed: 11'], axis=1)
print(y.head())
print(X.head())
from sklearn.model_selection import train_test_split
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.3, random_state=38, shuffle=True)
from sklearn.linear_model import LinearRegression
model = LinearRegression()
model.fit(X,y)
predicted = model.predict(test_X)
print("Predictions:", predicted[:5])
for p in zip(train_X.columns, model.coef_):
print("Intercept for {}: {:.3}".format(p[0], p[1]))
from sklearn.metrics import mean_squared_error
rmse = np.sqrt(mean_squared_error(predicted, test_y))
print("RMSE:", rmse)
r2 = model.score(test_X, test_y)
print("R squared:", r2) # 0.54 comparing to 0.02 before cleaning the data

View File

@ -1,5 +1,6 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import pandas as pd
import matplotlib.pyplot as plt
@ -106,3 +107,58 @@ def main():
if __name__ == "__main__":
main()
# zadanie dodatkowe
import sklearn
import pandas as pd
import numpy as np
dane = pd.read_csv("mieszkania.csv")
print(dane.head())
print(dane.columns)
# check data for outliers
from matplotlib import pyplot as plt
plt.scatter(dane['SqrMeters'], dane['Expected'], color='g')
plt.show()
# remove all data points that have expected price <= 500.000 and living area <= 200 sqrt meters
plt.scatter(dane['Rooms'], dane['Expected'], color='g')
plt.show()
# remove all data points that represent flats with more than 8 rooms
flats = dane[(dane['Rooms'] < 10) & (dane['SqrMeters'] <= 200) & (dane['Expected'] <= 500000)]
print(flats.head(20))
y = flats['Expected']
X = flats.drop(['Id', 'Expected', 'Floor', 'Location',
'Description', 'Unnamed: 7', 'Unnamed: 8', 'Unnamed: 9', 'Unnamed: 10', 'Unnamed: 11'], axis=1)
print(y.head())
print(X.head())
from sklearn.model_selection import train_test_split
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.3, random_state=38, shuffle=True)
from sklearn.linear_model import LinearRegression
model = LinearRegression()
model.fit(X,y)
predicted = model.predict(test_X)
print("Predictions:", predicted[:5])
for p in zip(train_X.columns, model.coef_):
print("Intercept for {}: {:.3}".format(p[0], p[1]))
from sklearn.metrics import mean_squared_error
rmse = np.sqrt(mean_squared_error(predicted, test_y))
print("RMSE:", rmse)
r2 = model.score(test_X, test_y)
print("R squared:", r2) # 0.54 comparing to 0.02 before cleaning the data

View File

@ -7,10 +7,10 @@
import pandas as pd
"""
2. Wczytaj zbiór danych `311.csv` do zniennej data.
2. Wczytaj zbiór danych `311.csv` do zmiennej data.
"""
data = pd.read_csv("labs06/311.csv")
data = pd.read_csv("311.csv", low_memory=False)
"""
3. Wyświetl 5 pierwszych wierszy z data.