from sklearn.tree import DecisionTreeClassifier
from sklearn.preprocessing import LabelEncoder

df = pd.read_csv('/content/iris.csv')
df.info()
encoder = LabelEncoder()
df["variety"] = encoder.fit_transform(df["variety"])
df.info()
X = df.iloc[:,:-1] #df.drop(columns=["speices"])
y = df.iloc[:,-1] #df["species"]
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=42)
dtc = DecisionTreeClassifier()
dtc.fit(X_train,y_train)
y_pred = dtc.predict(X_test)
print(y_test,y_pred)


from sklearn.metrics import accuracy_score,classification_report,confusion_matrix

accuracy = accuracy_score(y_pred,y_test)
print(accuracy)
print(classification_report(y_pred,y_test))
print(confusion_matrix(y_pred,y_test))


# prompt: Visualize insights of Above decision tree classification on iris dataset
from sklearn import tree
import matplotlib.pyplot as plt

plt.figure(figsize=(15,10))
tree.plot_tree(dtc,filled=True,feature_names=X.columns,class_names=['0','1','2'])
plt.show()