python
import pandas as pd
data = pd.read_csv("data.csv")
data = data.drop_duplicates()
data = data.fillna(0)
data["value"] = data["value"].apply(lambda x: x if x > 0 else 0)
print(data.head())
python
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
scaler = StandardScaler()
scaled_data = scaler.fit_transform(data)
minmax_scaler = MinMaxScaler()
normalized_data = minmax_scaler.fit_transform(data)
encoder = OneHotEncoder()
encoded_data = encoder.fit_transform(data)
print(scaled_data)
print(normalized_data)
print(encoded_data)
python
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
count_vectorizer = CountVectorizer()
word_count = count_vectorizer.fit_transform(text_data)
# TF-IDF
tfidf_vectorizer = TfidfVectorizer()
tfidf_data = tfidf_vectorizer.fit_transform(text_data)
print(word_count)
print(tfidf_data)
