#!/usr/bin/env python
# coding: utf-8

# In[1]:


import pandas as pd
import numpy as np
import os
from glob import glob


# In[2]:


df_activity = pd.read_csv("activities.csv")


# In[3]:


def segmentation(x_data,y,overlap_rate,time_window):
    
    seg_data = []
    overlap = int((1 - overlap_rate)*time_window)
    y_segmented_list = []
    
    for i in range(0,x_data.shape[0],overlap):
        seg_data.append(x_data[i:i+time_window])
        y_segmented_list.append(y)

    return seg_data,y_segmented_list


# In[4]:


def handle_missing_values(df):
    df['x']=df['x'].replace(0, np.nan)
    df['y']=df['y'].replace(0, np.nan)
    df['z']=df['z'].replace(0, np.nan)
    return df


# In[5]:


def load_data(csv_file):

    y_list = []
    x_data_list = []

    csv_df = pd.read_csv(csv_file)
    csv_df = handle_missing_values(csv_df)
    csv_df.dropna(inplace=True)
    x_data = csv_df.values
    act_id = get_act_id(int(os.path.splitext(os.path.basename(csv_files[0]))[0].replace("segment","")))
    
    return x_data,act_id


# In[6]:


def get_act_id(seg_id):
    seg = df_activity[df_activity["segment_id"]==seg_id]
    activity_id = seg["activity_id"].values
    return int(activity_id)


# In[7]:


# get features (std,avg,max,min)
def get_features(x_data):
    features = []
    for i in range(x_data.shape[1]):
        # std
        features.append(x_data.T[i].std(ddof=0))
        # avg
        features.append(np.average(x_data.T[i]))
        # max
        features.append(np.max(x_data.T[i]))
        # min
        features.append(np.min(x_data.T[i]))
    return features


# In[8]:


csv_files = glob("train/*")


# In[9]:


x_data,y = load_data(csv_files[0])


# # overroll window feature extraction

# In[10]:


x_feature = get_features(x_data)
print(x_feature)


# # feature extraction after segmentetion 

# In[11]:


seg_data_list,y_seg_list = segmentation(x_data,y,overlap_rate=0.5,time_window=10)


# In[12]:


x_feature_list = []
for seg_data in seg_data_list:
    x_feature_list.append(get_features(seg_data))


# In[13]:


for x_feature in zip(x_feature_list):
    print(x_feature)