# Ceteris Lab downloadable Python script
# Course: Fundamentals of Python for Financial Econometrics

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

docs = ["inflation rose after energy prices increased", "energy costs pushed inflation higher", "the football match ended in a draw"]
X = TfidfVectorizer().fit_transform(docs)
print(cosine_similarity(X[0], X).round(3).tolist()[0])

from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression
from sklearn.feature_extraction.text import TfidfVectorizer

texts = ["flood warning issued", "sunny picnic today", "earthquake reported", "great concert tonight"]
labels = [1, 0, 1, 0]
pipe = Pipeline([("tfidf", TfidfVectorizer()), ("model", LogisticRegression())]).fit(texts, labels)
print(pipe.predict(["storm warning tonight"]).tolist())

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
X = TfidfVectorizer().fit_transform(docs)
print(cosine_similarity(X[0], X).round(3).tolist()[0])
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression