python
import pandas as pd
dataframe = pd.read_csv('data.csv')
dataframe = pd.read_excel('data.xlsx')
sql_query = 'SELECT * FROM table'
dataframe = pd.read_sql(sql_query, connection)
python
python
python
from sklearn.feature_extraction.text import CountVectorizer
corpus = ['This is the first document.', 'This document is the second document.']
vectorizer = CountVectorizer()
X = vectorizer.fit_transform(corpus)
from sklearn.feature_selection import SelectKBest, f_classif
selector = SelectKBest(f_classif, k=20)
X_selected = selector.fit_transform(X, y)
python
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
model = LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
python
from sklearn.model_selection import GridSearchCV
param_grid = {'C': [0.1, 1, 10], 'kernel': ['linear', 'rbf']}
svm_model = SVC()
grid_search = GridSearchCV(estimator=svm_model, param_grid=param_grid, cv=5)
grid_search.fit(X_train, y_train)
best_params = grid_search.best_params_
best_score = grid_search.best_score_
python
import nltk
text = 'This is a sentence.'
tokens = nltk.word_tokenize(text)
pos_tags = nltk.pos_tag(tokens)
python
from nltk.classify import NaiveBayesClassifier
from nltk.sentiment import SentimentIntensityAnalyzer
train_data = [('Text 1', 'Category 1'), ('Text 2', 'Category 2')]
classifier = NaiveBayesClassifier.train(train_data)
text = 'This is a test text.'
category = classifier.classify(text)
sia = SentimentIntensityAnalyzer()
sentiment_scores = sia.polarity_scores(text)
python
from nltk.sem import relextract
from nltk.chunk import ne_chunk
text = 'John loves Mary.'
tree = nltk.ParentedTree.fromstring('(S (NP (NNP John)) (VP (VBZ loves) (NP (NNP Mary))))')
relextract.tree2semi_rel(tree)
text = 'John works at Google.'
tokens = nltk.word_tokenize(text)
ne_chunks = ne_chunk(nltk.pos_tag(tokens))
