import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
ds = pd.read_csv('../dataset/placement_clean.csv')
ds.head()
X = ds.iloc[:, 1:-1].values
y = ds.iloc[:, -1].values
print(X)
print(y)
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [0, 2, 4, 5, 7, 8, 9])], remainder='passthrough')
X = np.array(ct.fit_transform(X))
print(X)
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
y = le.fit_transform(y)
print(y)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 1)
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
print(X_train)
from sklearn.tree import DecisionTreeClassifier
classifier = DecisionTreeClassifier(criterion = 'entropy', random_state = 0)
classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
from sklearn.metrics import precision_score
precision_score(y_test, y_pred, average='weighted')
from sklearn.metrics import f1_score
f1_score(y_test, y_pred, average='weighted')
from sklearn.metrics import recall_score
recall_score(y_test, y_pred, average='weighted')