# ---
# jupyter:
#   jupytext:
#     formats: ipynb,py:percent
#     text_representation:
#       extension: .py
#       format_name: percent
#       format_version: '1.3'
#       jupytext_version: 1.13.0
#   kernelspec:
#     display_name: straw2analysis
#     language: python
#     name: straw2analysis
# ---

# %% 
import sys, os

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import recall_score, f1_score

nb_dir = os.path.split(os.getcwd())[0]
if nb_dir not in sys.path:
    sys.path.append(nb_dir)

from machine_learning.cross_validation import CrossValidation
from machine_learning.preprocessing import Preprocessing
from machine_learning.feature_selection import FeatureSelection

# %% 
df = pd.read_csv("../data/stressfulness_event_with_speech/input_appraisal_stressfulness_event_mean.csv")
index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
df.set_index(index_columns, inplace=True)

# Create binary target 
bins = [-1, 0, 4] # bins for stressfulness (0-4) target
df['target'], edges = pd.cut(df.target, bins=bins, labels=[0, 1], retbins=True, right=True) #['low', 'medium', 'high']


nan_cols = df.columns[df.isna().any()].tolist()
df[nan_cols] = df[nan_cols].fillna(round(df[nan_cols].median(), 0))

cv = CrossValidation(data=df, cv_method="logo")

categorical_columns = ["gender", "startlanguage", "mostcommonactivity", "homelabel"]
interval_feature_list, other_feature_list = [], []

# %%
for split in cv.get_splits():
    train_X, train_y, test_X, test_y = cv.get_train_test_sets(split)
    pre = Preprocessing(train_X, train_y, test_X, test_y)
    pre.one_hot_encode_train_and_test_sets(categorical_columns)
    train_X, train_y, test_X, test_y = pre.get_train_test_sets()
    
    
    print(train_X.shape, test_X.shape)
    # Predict before feature selection
    rfc = RandomForestClassifier(n_estimators=10)
    rfc.fit(train_X, train_y)
    predictions = rfc.predict(test_X)
    
    print("Recall:", recall_score(test_y, predictions))
    print("F1:", f1_score(test_y, predictions))
    
    # Feature selection on train set
    train_groups, test_groups = cv.get_groups_sets(split)

    fs = FeatureSelection(train_X, train_y, train_groups) 
    selected_features = fs.select_features(n_min=20, n_max=29, k=40,
                                           ml_type="classification_bin", 
                                           metric="recall", n_tolerance=20)
    
    train_X = train_X[selected_features]
    test_X = test_X[selected_features]
    
    print(selected_features)
    print(len(selected_features))
    
    # Predict after feature selection    
    rfc = RandomForestClassifier(n_estimators=500)
    rfc.fit(train_X, train_y)
    predictions = rfc.predict(test_X)
    
    print("Recall:", recall_score(test_y, predictions))
    print("F1:", f1_score(test_y, predictions))
    
    break

# %%