task02 **dodatkowe (labs06) done

labs06/model.py

@@ -0,0 +1,87 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""*(dodatkowe)*: Korzystając z pakietu *sklearn* zbuduj model regresji liniowej,
+która będzie wyznaczać cenę mieszkania na podstawie wielkości mieszkania i liczby pokoi."""
+
+#import bibliotek
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import sklearn
+from sklearn import linear_model
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_squared_error
+import math
+
+#wczytanie danych
+dane = pd.read_csv('mieszkania.csv', sep = ',', encoding = 'utf-8')
+dane = pd.DataFrame(dane)
+
+#analiza korelacji
+print(dane.corr())
+#korelacja niewielka dodatnia pomiedzy SqrMeters, a Expected = 0.109640
+#korelacja niewielka dodatnia pomiedzy Rooms, a Expected = 0.081177
+#niska korelaje pokazuje wykres rozrzutu
+dane.plot.scatter(x='SqrMeters', y='Expected')
+plt.show()
+
+#data preparation
+#X -independent variables
+#Y -dependent variable
+
+X = dane[['SqrMeters', 'Rooms' ]]
+X= pd.DataFrame(X)
+
+Y = dane['Expected']
+
+#splitting data into a training and test set:
+X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.20, random_state=1)
+
+#train LinearRegression model using the training set of data
+lm = linear_model.LinearRegression()
+lm.fit(X_train, Y_train)
+
+# coefficients of the model
+for idx, col_name in enumerate(X_train.columns):
+    print("The coefficient for {} is {}".format(col_name, lm.coef_[idx]))
+
+# intercept of the model
+intercept = lm.intercept_
+print("The intercept for our model is {}".format(intercept))
+
+#linear model : 123969.05-34261.86*X1+5299.47*X2
+
+#R^2 proportion of variability in Y that is explained by X in model =  accuracy of regression models
+#It seems that 0.78% of the variability in Y can be explained using X
+print(lm.score(X_test, Y_test))
+
+#predykcja
+#comparing the prediction for the test data set (data not used for training) with the ground truth for the data test set
+y_predict = lm.predict(X_test)
+
+lm_mse = mean_squared_error(y_predict, Y_test)
+
+#It seems that we are an average of 1148825.67 away from the ground truth when making predictions on our test set.
+print(lm_mse)
+print(math.sqrt(lm_mse))
+
+print('--------')
+#print(X_test['SqrMeters'])
+#linear model plot - how our model plots against our test data.
+plt.scatter(X_test['SqrMeters'], Y_test,  color='black')
+plt.plot(X_test['SqrMeters'], y_predict, color='blue', linewidth=2)
+
+plt.scatter(X_test['SqrMeters'], Y_test,  color='black')
+plt.plot(X_test['SqrMeters'], y_predict, color='blue', linewidth=2)
+
+plt.xticks(())
+plt.yticks(())
+
+plt.show()
+
+#prediction using made up data
+# SqrMeters:45
+# Rooms: 3
+print(lm.predict([[45, 3]]))
+# Expected price:  259659.47