Lab_ML(17/02/25)

# %%
import pandas as pd
import numpy as np
df = pd.read_csv("https://raw.githubusercontent.com/codebasics/py/master/ML/9_decision_tree/Exercise/titanic.csv")
df.head()


# %%
import pandas
from sklearn import model_selection
from sklearn.linear_model import LogisticRegression
url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv"
names = ['preg','plas','pres','skin','test','mass','pedi','age','class']
dataframe = pandas.read_csv(url,names =names)
dataframe

# %%
dataframe.isnull().sum()

# %%
df.drop(['PassengerId','Name','SibSp','Parch','Ticket','Cabin','Embarked'],axis = 'columns',inplace =True)
df.head()

# %%
from sklearn.preprocessing import LabelEncoder
L_Sex = LabelEncoder()

# %%
df['Gender Code']=L_Sex.fit_transform(df['Sex'])
df

# %%
df_new = df.drop(['Sex','Survived'],axis='columns')
df_new

# %%
df_new.Age = df_new.Age.fillna(df_new.Age.mean())
df_new

# %%
target = df['Survived']
target

# %%
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(df_new,target,test_size=0.2)

# %%
len(X_train)

# %%
len(X_test)

# %%
len(y_train)

# %%
len(y_test)

# %%
from sklearn import tree
model = tree.DecisionTreeClassifier()

model.fit(X_train,y_train)

# %%
y_predicted =  model.predict(X_test)

# %%
from sklearn.metrics import confusion_matrix,classification_report
matrix = confusion_matrix(y_test, y_predicted,labels=[1,0])

# %%
print('confusion matrix \n',matrix)

# %%
from matplotlib import pyplot as plt
import pandas as pd
import seaborn as sns

# %%
def print_confusion_matrix(confusion_matrix, class_name, figsize=(10,7),fontsize=14):
    df_cm=pd.DataFrame(
        confusion_matrix, index=class_name, columns=class_name,
    )
    fig = plt.figure(figsize=figsize)
    try:
        heatmap = sns.heatmap(df_cm, annot=True, fmt='d')
    except ValueError:
        raise ValueError("Confusion matrix values must be integers.")
    heatmap.yaxis.set_ticklabels(heatmap.yaxis.get_ticklabels(), rotation=0, ha='right', fontsize=fontsize)
    heatmap.xaxis.set_ticklabels(heatmap.yaxis.get_ticklabels(), rotation=45, ha='right', fontsize=fontsize)
    plt.ylabel('Truth')
    plt.xlabel('Prediction')

print_confusion_matrix(matrix, ["Survived","Not Survived"])

# %%
matrix = classification_report(y_test,y_predicted,labels=[1,0])
print('classification report : \n', matrix)

# %%
model.score(X_train,y_train)

# %%
model.score(X_test,y_test)

# %%
model.score(X_test,y_predicted)

# %%
from sklearn import model_selection

# %%
kfold = model_selection.KFold(n_splits=10,random_state=4,shuffle=True)
scoring = 'accuracy'
results = model_selection.cross_val_score(model, X_test, y_predicted, cv=kfold, scoring=scoring)
print("Accuracy: %.3f "%(results.mean()))

# %%
scoring = 'roc_auc'
results = model_selection.cross_val_score(model, X_test, y_predicted, cv=kfold, scoring=scoring)
print("Accuracy: %.3f(%.3f) "%(results.mean(),results.std()))