from collections import Counter

import numpy as np
from sklearn.feature_extraction import DictVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline

from classifiers.cleaning import LowercaseTransformer, PunctuationRemover


class FeatureExtractor:
    def fit(self, X, y=None):
        return self

    def transform(self, X):
        return [self.extract_features(msg) for msg in X]

    def extract_features(self, message):
        return dict(Counter(message.split()))


class BagOfWordsClassifier:
    def fit(self, X, y):
        self._pipeline = Pipeline([
            ("lowercase", LowercaseTransformer()),
            ("punctuation", PunctuationRemover()),
            ("features", FeatureExtractor()),
            ("vectorizer", DictVectorizer()),
            ("classifier", LogisticRegression(max_iter=1000)),
        ])
        y_binary = (np.array(y) == "spam").astype(int)
        self._pipeline.fit(X, y_binary)
        return self

    def predict(self, X):
        y_binary = self._pipeline.predict(X)
        return np.where(y_binary == 1, "spam", "ham")

    def feature_weights(self, top_n=10):
        vectorizer = self._pipeline.named_steps["vectorizer"]
        classifier = self._pipeline.named_steps["classifier"]
        names = vectorizer.get_feature_names_out()
        weights = classifier.coef_[0]
        pairs = sorted(zip(names, weights), key=lambda x: x[1])
        half = top_n // 2
        return pairs[-half:][::-1] + pairs[:half]