MLP3

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

from google.colab import files
uploaded = files.upload()

veriler = pd.read_csv("HousingData.csv")
veriler.head()

veriler.isnull().sum()

veriler.dtypes

veriler.corr()

plt.figure(figsize=(12, 12))
heatmap = sns.heatmap(veriler.corr(), vmin=-1, vmax=1, annot=True)
heatmap.set_title('Correlation Heatmap', fontdict={'fontsize':12}, pad=12);


### **EKSİK VERİLERİMİZ VAR**
### **    Simple İMPUTER YÖNTEMİ**


x = veriler.iloc[:, :13].values  # İlk 13 özellik sütununu X olarak seç
y = veriler.iloc[:, 13].values   # MEDV sütununu y olarak seç

from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')
imputer.fit(x[:, :13])
x[:, :13] = imputer.transform(x[:, :13])

np.isnan(np.sum(x))      #BOŞ VERİ VAR MI SORDUK YOK

from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(x, y, test_size=0.33, random_state=42)

from sklearn import linear_model
from sklearn.linear_model import LinearRegression

model = LinearRegression()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)

from sklearn.metrics import explained_variance_score, mean_absolute_error, mean_squared_error
from sklearn.metrics import median_absolute_error, r2_score

print("R-Kare: ", r2_score(y_test, y_pred))
print("MAE: ", mean_absolute_error(y_test, y_pred))
print("MSE: ", mean_squared_error(y_test, y_pred))
print("MedAE: ", median_absolute_error(y_test, y_pred))
print("EVS: ", explained_variance_score(y_test, y_pred))

### **K EN YAKIN KOMŞU**

from sklearn.impute import KNNImputer
x_knn = veriler.iloc[:,:13].values
y = veriler.iloc[:,13].values
imputer = KNNImputer(n_neighbors=2,weights="uniform")
imputer.fit_transform(x_knn)

(x_knn==x).all()         # BOŞLUK YOKSA FALSE

print("NaN var mı: ", pd.DataFrame(x_knn).isnull().values.any())

from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(x_knn, y, test_size=0.33, random_state=42)

from sklearn import linear_model
from sklearn.linear_model import LinearRegression

model = LinearRegression()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)

from sklearn.metrics import explained_variance_score, mean_absolute_error, mean_squared_error
from sklearn.metrics import median_absolute_error, r2_score

print("R-Kare: ", r2_score(y_test, y_pred))
print("MAE: ", mean_absolute_error(y_test, y_pred))
print("MSE: ", mean_squared_error(y_test, y_pred))
print("MedAE: ", median_absolute_error(y_test, y_pred))
print("EVS: ", explained_variance_score(y_test, y_pred))