import pandas as pd
import numpy as np
import os

from sklearn.datasets import load_iris
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import f_classif

features_dic = {}
results_dic = {}

script_dir = os.path.dirname(__file__)
rel_path = "bialaczka_switched.xls"
abs_file_path = os.path.join(script_dir, rel_path)

dataExcel = pd.read_excel(abs_file_path, nrows=410)
df = pd.DataFrame(dataExcel)

feature_data = df.iloc[:, :-2]
diagnose_classes = np.array(df['Klasa'])

# Create an SelectKBest object to select features with two best ANOVA F-Values
fvalue_selector = SelectKBest(f_classif)

# Apply the SelectKBest object to the features and target
feature_data_kbest = fvalue_selector.fit(feature_data, diagnose_classes)

ranking = fvalue_selector.scores_

ranking_ = pd.DataFrame(ranking)