5.Decision Tree Classification AND K-Neareast Nrighbour
Sun Nov 03 2024 13:27:38 GMT+0000 (Coordinated Universal Time)
#Decision Tree Classification
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score,classification_report,confusion_matrix
import pandas as pd
iris = load_iris()
df = pd.DataFrame(data=iris.data, columns=iris.feature_names)
df['species'] = iris.target
print(df.head())
print(df.info())
X = df.drop('species', axis=1)
y = df['species']
x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=42)
model = DecisionTreeClassifier()
model.fit(x_train,y_train)
y_pred = model.predict(x_test)
accuracy = accuracy_score(y_test,y_pred)
print("Accuracy:",accuracy)
print("Classification Report:\n",classification_report(y_test,y_pred))
print("Confusion Matrix:\n",confusion_matrix(y_test,y_pred))
output:
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) \
0 5.1 3.5 1.4 0.2
1 4.9 3.0 1.4 0.2
2 4.7 3.2 1.3 0.2
3 4.6 3.1 1.5 0.2
4 5.0 3.6 1.4 0.2
species
0 0
1 0
2 0
3 0
4 0
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150 entries, 0 to 149
Data columns (total 5 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 sepal length (cm) 150 non-null float64
1 sepal width (cm) 150 non-null float64
2 petal length (cm) 150 non-null float64
3 petal width (cm) 150 non-null float64
4 species 150 non-null int64
dtypes: float64(4), int64(1)
memory usage: 6.0 KB
None
Accuracy: 1.0
Classification Report:
precision recall f1-score support
0 1.00 1.00 1.00 10
1 1.00 1.00 1.00 9
2 1.00 1.00 1.00 11
accuracy 1.00 30
macro avg 1.00 1.00 1.00 30
weighted avg 1.00 1.00 1.00 30
Confusion Matrix:
[[10 0 0]
[ 0 9 0]
[ 0 0 11]]
2.#K-Neareast Nrighbour
#K-Neareast Nrighbour
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score,classification_report,confusion_matrix
from sklearn.neighbors import KNeighborsClassifier
iris = load_iris()
df = pd.DataFrame(data=iris.data,columns=iris.feature_names)
df['species']=iris.target
print(df.head())
print(df.info())
x = df.drop('species',axis=1)
y = df['species']
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state=42)
knn = KNeighborsClassifier(n_neighbors=1)
knn.fit(x_train,y_train)
y_pred = knn.predict(x_test)
accuracy = accuracy_score(y_test,y_pred)
print("Accuracy:",accuracy)
print("Classification Report:\n",classification_report(y_test,y_pred))
print("Confusion Matrix:\n",confusion_matrix(y_test,y_pred))
output:
]
#K-Neareast Nrighbour
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score,classification_report,confusion_matrix
from sklearn.neighbors import KNeighborsClassifier
iris = load_iris()
df = pd.DataFrame(data=iris.data,columns=iris.feature_names)
df['species']=iris.target
print(df.head())
…print("Confusion Matrix:\n",confusion_matrix(y_test,y_pred))
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) \
0 5.1 3.5 1.4 0.2
1 4.9 3.0 1.4 0.2
2 4.7 3.2 1.3 0.2
3 4.6 3.1 1.5 0.2
4 5.0 3.6 1.4 0.2
species
0 0
1 0
2 0
3 0
4 0
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150 entries, 0 to 149
Data columns (total 5 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 sepal length (cm) 150 non-null float64
1 sepal width (cm) 150 non-null float64
2 petal length (cm) 150 non-null float64
3 petal width (cm) 150 non-null float64
4 species 150 non-null int64
dtypes: float64(4), int64(1)
memory usage: 6.0 KB
None
Accuracy: 1.0
Classification Report:
precision recall f1-score support
0 1.00 1.00 1.00 10
1 1.00 1.00 1.00 9
2 1.00 1.00 1.00 11
accuracy 1.00 30
macro avg 1.00 1.00 1.00 30
weighted avg 1.00 1.00 1.00 30
Confusion Matrix:
[[10 0 0]
[ 0 9 0]
[ 0 0 11]]
Comments