Question

how to apply decison tree on a vector of strings ?

Answer 1

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split

# Example vector of strings
vector_of_strings = [
    "This is the first string",
    "Another string to process",
    "Final string for the example"
]
labels = [0, 1, 0]  # Example labels for classification

# Initialize TF-IDF vectorizer
vectorizer = TfidfVectorizer()

# Fit and transform the vector of strings
X = vectorizer.fit_transform(vector_of_strings)

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, labels, test_size=0.2, random_state=42)

# Initialize decision tree classifier
clf = DecisionTreeClassifier()

# Train the classifier
clf.fit(X_train, y_train)

# Predict on test data
y_pred = clf.predict(X_test)

# Evaluate accuracy or other metrics
accuracy = clf.score(X_test, y_test)
print(f"Accuracy: {accuracy}")

Answer 2

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split

# Example vector of strings
vector_of_strings = [
    "This is the first string",
    "Another string to process",
    "Final string for the example"
]
labels = [0, 1, 0]  # Example labels for classification

# Initialize TF-IDF vectorizer
vectorizer = TfidfVectorizer()

# Fit and transform the vector of strings
X = vectorizer.fit_transform(vector_of_strings)

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, labels, test_size=0.2, random_state=42)

# Initialize decision tree classifier
clf = DecisionTreeClassifier()

# Train the classifier
clf.fit(X_train, y_train)

# Predict on test data
y_pred = clf.predict(X_test)

# Evaluate accuracy or other metrics
accuracy = clf.score(X_test, y_test)
print(f"Accuracy: {accuracy}")