Lab_ML(24/02/25)

# %%
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import pandas as pd
import numpy as np

# %%
dataset_dict = {
    'Outlook': ['sunny', 'sunny', 'overcast', 'rainy', 'rainy', 'rainy', 'overcast', 'sunny', 'sunny', 'rainy', 'sunny', 'overcast', 'overcast', 'sunny', 'rainy', 'sunny', 'overcast', 'overcast', 'rainy', 'rainy', 'overcast', 'sunny', 'sunny', 'rainy', 'rainy', 'overcast', 'sunny', 'overcast', 'overcast', 'rainy'],
    'Temperature': [85.0, 80.0, 83.0, 70.0, 68.0, 65.0, 64.0, 72.0, 69.0, 75.0, 75.0, 72.0, 69.0, 81.0, 71.0, 81.0, 74.0, 76.0, 78.0, 82.0, 67.0, 83.0, 67.0, 79.0, 80.0, 81.0, 75.0, 85.0, 76.0, 79.0],
    'Humidity': [85.0, 90.0, 78.0, 96.0, 80.0, 70.0, 65.0, 95.0, 70.0, 80.0, 90.0, 75.0, 88.0, 88.0, 92.0, 85.0, 75.0, 92.0, 90.0, 82.0, 67.0, 98.0, 80.0, 92.0, 90.0, 82.0, 95.0, 95.0, 93.0, 92.0],
    'Wind': [False, True, False, False, False, True, True, False, False, False, True, True, False, True, True, False, False, True, False, False, True, True, False, False, True, True, False, True, False, False],
    'Play': ['No', 'No', 'Yes', 'Yes', 'Yes', 'No', 'Yes', 'No', 'Yes', 'Yes', 'Yes', 'Yes', 'Yes', 'No', 'No', 'Yes', 'Yes', 'No', 'No', 'Yes', 'Yes', 'No', 'Yes', 'No', 'Yes', 'Yes', 'No', 'Yes', 'Yes', 'No']
}
# Create the DataFrame
original_df = pd.DataFrame(dataset_dict)

# Print the DataFrame
print(original_df)

# %%
from sklearn.preprocessing import StandardScaler

# %%
df = pd.get_dummies(original_df, columns=['Outlook'],prefix='',prefix_sep='',dtype=int)
df['Wind'] = df['Wind'].astype(int)
df['Play'] = (df['Play']=='Yes').astype(int)
df = df[['sunny','rainy','overcast','Temperature','Humidity','Wind','Play']]

# %%
X,y = df.drop(columns='Play'),df['Play']
X_train,X_test,y_train,y_test = train_test_split(X,y,train_size = 0.5,shuffle=False)

# %%
scaler = StandardScaler()
float_cols = X_train.select_dtypes(include=['float64']).columns
X_train[float_cols] = scaler.fit_transform(X_train[float_cols])
X_test[float_cols] = scaler.transform(X_test[float_cols])

# %%
print(pd.concat([X_train,y_train],axis=1).round(2),'\n')
print(pd.concat([X_test,y_test],axis=1).round(2),'\n')

# %%
k = 5

# %%
from sklearn.neighbors import KNeighborsClassifier

# %%
distance_metric = 'euclidean'
knn_clf = KNeighborsClassifier(n_neighbors=k,metric=distance_metric)
knn_clf.fit(X_train,y_train)

# %%
y_pred = knn_clf.predict(X_test)
print("Label    :",list(y_test))
print("Prediction   :",list(y_pred))

# %%
accuracy = accuracy_score(y_test,y_pred)
print(f'accuracy: {accuracy*100}%')

# %%
labels,predictions,accuracies = list(y_test),[],[]

# %%
k_list = [3,5,7]
for k in k_list:
    knn_clf = KNeighborsClassifier(n_neighbors=k)
    knn_clf.fit(X_train,y_train)
    y_pred = knn_clf.predict(X_test)
    predictions.append(list(y_pred))
    accuracies.append(accuracy_score(y_test,y_pred)*100)

# %%
df_predictions = pd.DataFrame({'Label':labels})
for k, pred in zip(k_list,predictions):
    df_predictions[f'k = {k}'] = pred

# %%
df_accuracies = pd.DataFrame({'Accuracy ':accuracies},index=[f'k = {k}' for k in k_list]).T

# %%
print(df_predictions)
print(df_accuracies)