from glob import glob
import numpy as np
import scipy as sp
import pandas as pd



from sklearn.cluster import KMeans
from sklearn.metrics import accuracy_score, confusion_matrix

import os

from sklearn.ensemble import RandomForestClassifier

og_data_columns = 4


def apply_k_means_clustering(data, kmeans):
    hist = np.zeros((len(kmeans.cluster_centers_),))
    for x in kmeans.predict(data):
        hist[x]+=1
    print(hist)
    return hist

def quantize_flattened_data(data, length):
    # print("quantizing the data")
    # print(data)
    quantile_length = length*og_data_columns
    rows = int(len(data)/quantile_length)
    return np.resize(data, (rows, quantile_length))

def load_data(data_dir):
    data = []
    for root, dirs, files in os.walk(data_dir):
        if root is data_dir:
            continue
        for file in files:
            data.append([os.path.basename(root), pd.read_csv(os.path.join(root, file)).values.flatten()])
    return pd.DataFrame(data, columns=["exercise", "flat_data"])

train_data = load_data("./train")
test_data = load_data("./test")
# val_data = load_data("./val")

quant_len = 3

train_data["quantized_data"] = train_data["flat_data"].apply(lambda x : quantize_flattened_data(x, quant_len))
test_data["quantized_data"] = test_data["flat_data"].apply(lambda x : quantize_flattened_data(x, quant_len))


linked_data = train_data["quantized_data"][0]

for x in train_data["quantized_data"]:
    linked_data = np.append(linked_data, x, axis=0)

print(linked_data)

k_means_model = KMeans(n_clusters=25, n_init=15, max_iter= 500).fit(linked_data)

print(k_means_model.cluster_centers_)

train_data["histogram"] = train_data["quantized_data"].apply(lambda x: apply_k_means_clustering(x, k_means_model))
test_data["histogram"] = test_data["quantized_data"].apply(lambda x: apply_k_means_clustering(x, k_means_model))
print(train_data)

clf = RandomForestClassifier(n_estimators=50)
print(train_data["histogram"].values)

clf.fit([x for x in train_data["histogram"]], train_data["exercise"].values)
results = clf.predict([x for x in test_data["histogram"]])
print(results)
print(test_data["exercise"].values)

print(accuracy_score( test_data["exercise"].values,results ))
print(confusion_matrix( test_data["exercise"].values,results))