import pandas as pd
import numpy as np
from matplotlib.pyplot import subplots

house = pd.read_csv('house.csv')
house.head(3)

house = house[house['Bldg Type'] == '1Fam']
house = house[house['Sale Condition'] == 'Normal']
sales = house[['SalePrice', '1st Flr SF', '2nd Flr SF', 'Total Bsmt SF', 
               'Garage Area', 'Wood Deck SF', 'Open Porch SF', 'Lot Area', 
               'Year Built', 'Yr Sold']]
sales.head(3)

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import PolynomialFeatures
from sklearn.metrics import r2_score, mean_squared_error
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression

X = sales[['1st Flr SF', '2nd Flr SF', 'Open Porch SF', 'Year Built']]
y = sales['SalePrice']

from sklearn.model_selection import train_test_split
# Assume X and y are your features and target variable

# Split data into training and testing sets (example)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create and fit the model
model = LinearRegression()
model.fit(X_train, y_train)

# Get the R² score
score = model.score(X_test, y_test)
print(f"Model R² Score: {score}")

Model R² Score: 0.7832171768278281

# Let us save all the predictor variables in X and the response in y
X = sales[['1st Flr SF', '2nd Flr SF']]
y = sales['SalePrice']

# Split data into training and testing sets (example)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)


# Fitting a polynomial of degree d
score = []
for d in range(1, 6):
    model = Pipeline([
            ("poly", PolynomialFeatures(degree=d, include_bias=False)),
            ("scaler", StandardScaler()),
            ("linreg", LinearRegression())
        ])
    model.fit(X_train, y_train)
    y_test_pred = model.predict(X_test)
    score.append(mean_squared_error(y_test_pred, y_test))
    print('R^2 score on test set with degree', d, ' : ', r2_score(y_test_pred, y_test))

fig, ax = subplots(figsize = (4, 4))
ax.plot(range(1, 6), score)

R^2 score on test set with degree 1  :  0.5636673108738282
R^2 score on test set with degree 2  :  0.5686254523419286
R^2 score on test set with degree 3  :  0.5603163173001231
R^2 score on test set with degree 4  :  0.6129129404922433
R^2 score on test set with degree 5  :  0.20652947636342744

[<matplotlib.lines.Line2D at 0x11ffb72b0>]

ckd = pd.read_csv('ckd.csv')
ckd = ckd[['Age', 'Blood Pressure', 'Blood Glucose Random', 'White Blood Cell Count', 'Red Blood Cell Count', 'Class']]
ckd

X = ckd[['Age', 'Blood Pressure', 'Blood Glucose Random', 'White Blood Cell Count', 'Red Blood Cell Count']]
y = ckd['Class']

# Create a train:test split of the data 
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.30, random_state=42, stratify=y
)

# We shall use the StandardScaler to scale the training dataset
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
# The transform method is then used to scale the test data using parameters
# obtained from the training data.
X_test_scaled = scaler.transform(X_test)

from sklearn.linear_model import LogisticRegression
logreg = LogisticRegression(max_iter=1000)

logreg.fit(X_train, y_train)
y_pred = logreg.predict(X_test)

from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
# Evaluate
print('Evaluation of Logistic Regression classification')
print("Accuracy:", accuracy_score(y_test, y_pred))
print("\nConfusion Matrix:")
print(confusion_matrix(y_test, y_pred))
print("\nClassification Report:")
print(classification_report(y_test, y_pred))

Evaluation of Logistic Regression classification
Accuracy: 0.9583333333333334

Confusion Matrix:
[[34  1]
 [ 1 12]]

Classification Report:
              precision    recall  f1-score   support

           0       0.97      0.97      0.97        35
           1       0.92      0.92      0.92        13

    accuracy                           0.96        48
   macro avg       0.95      0.95      0.95        48
weighted avg       0.96      0.96      0.96        48

from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=13)
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)

# Evaluate
print('Evaluation of KNN classification')
print("Accuracy:", accuracy_score(y_test, y_pred))
print("\nConfusion Matrix:")
print(confusion_matrix(y_test, y_pred))
print("\nClassification Report:")
print(classification_report(y_test, y_pred))

Evaluation of KNN classification
Accuracy: 0.8541666666666666

Confusion Matrix:
[[35  0]
 [ 7  6]]

Classification Report:
              precision    recall  f1-score   support

           0       0.83      1.00      0.91        35
           1       1.00      0.46      0.63        13

    accuracy                           0.85        48
   macro avg       0.92      0.73      0.77        48
weighted avg       0.88      0.85      0.83        48

	Order	PID	MS SubClass	MS Zoning	Lot Frontage	Lot Area	Street	Alley	Lot Shape	Land Contour	...	Pool QC	Fence	Misc Feature	Misc Val	Mo Sold	Yr Sold	Sale Type	Sale Condition	SalePrice
0	1	526301100	20	RL	141.0	31770	Pave	NaN	IR1	Lvl	...	NaN	NaN	NaN	0	5	2010	WD	Normal	215000
1	2	526350040	20	RH	80.0	11622	Pave	NaN	Reg	Lvl	...	NaN	MnPrv	NaN	0	6	2010	WD	Normal	105000
2	3	526351010	20	RL	81.0	14267	Pave	NaN	IR1	Lvl	...	NaN	NaN	Gar2	12500	6	2010	WD	Normal	172000

	SalePrice	1st Flr SF	Total Bsmt SF	Garage Area	Wood Deck SF	Open Porch SF	Lot Area	Year Built	Yr Sold
0	215000	1656	1080.0	528.0	210	62	31770	1960	2010
1	105000	896	882.0	730.0	140	0	11622	1961	2010
2	172000	1329	1329.0	312.0	393	36	14267	1958	2010

	Age	Blood Pressure	Blood Glucose Random	White Blood Cell Count	Red Blood Cell Count	Class
0	48	70	117	6700	3.9	1
1	53	90	70	12100	3.7	1
2	63	70	380	4500	3.8	1
3	68	80	157	11000	2.6	1
4	61	80	173	9200	3.2	1
...	...	...	...	...	...	...
153	55	80	140	6700	4.9	0
154	42	70	75	7800	6.2	0
155	12	80	100	6600	5.4	0
156	17	60	114	7200	5.9	0
157	58	80	131	6800	6.1	0