Dodano nowe pliki do repozytorium

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/ML9.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (ML9)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/ML9.iml" filepath="$PROJECT_DIR$/.idea/ML9.iml" />
+    </modules>
+  </component>
+</project>

neural network.py

@@ -0,0 +1,38 @@
+import pandas as pd
+import math
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from keras.models import Sequential
+from keras.layers import Dense
+from sklearn import metrics
+
+
+df = pd.read_csv('data.csv')
+
+scaler = StandardScaler()
+X = scaler.fit_transform(df.iloc[:, :-1])
+y = df.iloc[:, -1]
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+print("Podzielono zbiór na {} rekordów uczących i {} rekordów testowych".format(len(y_train), len(y_test)))
+
+model = Sequential()
+model.add(Dense(32, activation='relu', input_dim=(X_train.shape[1])))
+model.add(Dense(32, activation='relu'))
+model.add(Dense(1, activation='linear'))
+print("Stworzono sieć neuronową: \n")
+model.summary()
+model.compile(optimizer='adam', loss='mean_squared_error', metrics=["mae"])
+
+epochs = 1500
+model.fit(X_train, y_train, epochs=epochs, validation_data=(X_test, y_test))
+
+print("Zakończono trenowanie sieci neuronowej z wykorzystaniem biblioteki Keras.")
+
+predicted_prices = model.predict(X_test)
+
+rmse = math.sqrt(metrics.mean_squared_error(y_test, predicted_prices))
+mae = metrics.mean_absolute_error(y_test, predicted_prices)
+
+print('RMSE: {:.2f} zł'.format(rmse))
+print('MAE: {:.2f} zł'.format(mae))

regression (linear and Random Forest Tree).py

@@ -0,0 +1,38 @@
+import pandas as pd
+import math
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import LinearRegression
+from sklearn.ensemble import RandomForestRegressor
+from sklearn import metrics
+
+df = pd.read_csv('data.csv')
+
+scaler = StandardScaler()
+X = scaler.fit_transform(df.iloc[:, :-1])
+y = df.iloc[:, -1]
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+print("Podzielono zbiór na {} rekordów uczących i {} rekordów testowych".format(len(y_train), len(y_test)))
+
+regressor_lin = LinearRegression()
+regressor_lin.fit(X_train, y_train)
+print("\nWyuczono model regresjii liniowej:")
+predicted_prices_lin = regressor_lin.predict(X_test)
+
+rmse_lin = math.sqrt(metrics.mean_squared_error(y_test, predicted_prices_lin))
+mae_lin = metrics.mean_absolute_error(y_test, predicted_prices_lin)
+
+print('RMSE: {:.2f} zł'.format(rmse_lin))
+print('MAE: {:.2f} zł'.format(mae_lin))
+
+regressor_RF = RandomForestRegressor(random_state=8)
+regressor_RF.fit(X_train, y_train)
+print("\nWyuczono model regresji drzew Random Forest:")
+predicted_prices_RF = regressor_RF.predict(X_test)
+
+rmse_RF = math.sqrt(metrics.mean_squared_error(y_test, predicted_prices_RF))
+mae_RF = metrics.mean_absolute_error(y_test, predicted_prices_RF)
+
+print('RMSE: {:.2f} zł'.format(rmse_RF))
+print('MAE: {:.2f} zł'.format(mae_RF))

scraper.py

@@ -0,0 +1,35 @@
+import pandas as pd
+
+df_2311 = pd.read_csv('archive/apartments_pl_2023_11.csv')
+df_2312 = pd.read_csv('archive/apartments_pl_2023_12.csv')
+df_2401 = pd.read_csv('archive/apartments_pl_2024_01.csv')
+df_2402 = pd.read_csv('archive/apartments_pl_2024_02.csv')
+
+
+def pull_krakow(df):
+    df_krakow = df[df["city"] == 'krakow']
+    return df_krakow
+
+
+df_2311 = pull_krakow(df_2311)
+df_2312 = pull_krakow(df_2312)
+df_2401 = pull_krakow(df_2401)
+df_2402 = pull_krakow(df_2402)
+
+df_concatenated = pd.concat([df_2311, df_2312, df_2401, df_2402], ignore_index=True)
+
+sum = len(df_2311) + len(df_2312) + len(df_2401) + len(df_2402)
+print(sum)
+
+df_no_duplicates = df_concatenated.drop_duplicates(subset = ["squareMeters", "rooms", "floor", "centreDistance", "price"])
+print(len(df_no_duplicates))
+
+df_selected_columns = df_no_duplicates[["squareMeters", "rooms", "floor", "buildYear", "centreDistance", "poiCount", "price"]]
+
+df_na_dropped = df_selected_columns.dropna()
+
+print(len(df_na_dropped))
+
+df_na_dropped.to_csv('data.csv', index=False)
+
+print("Dane zapisane do data.csv.")