pos_hmean = term_freq_df2.pos_normcdf_hmean

y_val_predicted_proba = []
for t in x_validation:
    hmean_scores = [pos_hmean[w] for w in t.split() if w in pos_hmean.index]
    if len(hmean_scores) > 0:
        prob_score = np.mean(hmean_scores)
    else:
        prob_score = np.random.random()
    y_val_predicted_proba.append(prob_score)

pred = [1 if t > 0.56 else 0 for t in y_val_predicted_proba]

from sklearn.metrics import accuracy_score
accuracy_score(y_validation,pred)