Created
August 29, 2019 21:37
-
-
Save prrao87/94b47978c9167ecdf5f83270c0323969 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class TextBlobSentiment(Base): | |
"""Predict fine-grained sentiment classes using TextBlob.""" | |
def __init__(self, model_file: str=None) -> None: | |
super().__init__() | |
def score(self, text: str) -> float: | |
# pip install textblob | |
from textblob import TextBlob | |
return TextBlob(text).sentiment.polarity | |
def predict(self, train_file: None, test_file: str, lower_case: bool) -> pd.DataFrame: | |
df = self.read_data(test_file, lower_case) | |
df['score'] = df['text'].apply(self.score) | |
# Convert float score to category based on binning | |
df['pred'] = pd.cut(df['score'], | |
bins=5, | |
labels=[1, 2, 3, 4, 5]) | |
df = df.drop('score', axis=1) | |
return df |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment