data_preprocessing.py

np.random.seed(42)
df = (dataset
               .rename(columns={"Created At": "publication_date",
                                "Text": "tweet",                                
                                "Retweet Count" : "num_retweets",
                                "Username": "username",
                                "Classificacao": "sentiment"})
               .loc[:, ["publication_date", "tweet", "num_retweets",  "username", "sentiment"]])
df["publication_date"] = pd.to_datetime(df["publication_date"],infer_datetime_format=True)
df["sentiment"] = df["sentiment"].replace({"Negativo": 0, "Neutro": np.random.choice([0, 1]), "Positivo": 1})