File size: 4,557 Bytes
85a54f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
import os
from datetime import datetime, timedelta
import ccxt
import pandas as pd
#import numpy as np
import calendar
#from scipy import signal
from scipy.signal import savgol_filter
from pykalman import KalmanFilter


class HistoricalDataFetcher:

  def __init__(self,
               exchange_name='coinbasepro',
               symbol='BTC/USD',
               timeframe='1d',
               start_date=datetime(2015, 7, 1),
               end_date=datetime.now()):
    self.exchange = getattr(ccxt, exchange_name)()
    self.symbol = symbol
    self.timeframe = timeframe
    self.start_date = start_date
    self.end_date = end_date
    self.raw_path = f"data/{self.symbol.replace('/','')}"
    self.clean_path = f"data/clean_{self.symbol.replace('/','')}"

    # Crear la carpeta para los archivos raw si no existe
    if not os.path.exists(self.raw_path):
      os.makedirs(self.raw_path)
    # Crear la carpeta para los archivos limpios si no existe
    if not os.path.exists(self.clean_path):
      os.makedirs(self.clean_path)

  def fetch_data(self):
    start_date = self.start_date
    end_date = self.end_date

    while start_date < end_date:

      year = start_date.year
      month = start_date.month

      # Determine the number of days in the month
      num_days = calendar.monthrange(year, month)[1]

      # Calculate the start and end dates for the month
      since = self.exchange.parse8601(
        start_date.strftime('%Y-%m-%d') + 'T00:00:00Z')
      until = self.exchange.parse8601(
        (start_date + timedelta(days=num_days)).strftime('%Y-%m-%d') +
        'T23:59:59Z')

      print(f"Fetching data for {calendar.month_name[month]} {year}")

      # Get historical data for the month
      ohlcv = self.exchange.fetch_ohlcv(self.symbol,
                                        self.timeframe,
                                        since,
                                        limit=None,
                                        params={'end': until})

      # Convert the data to a pandas DataFrame
      df = pd.DataFrame(
        ohlcv, columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])

      # Convert the timestamp to a datetime and set it as the index
      df['timestamp'] = pd.to_datetime(df['timestamp'], unit='ms')
      df.set_index('timestamp', inplace=True)

      # Save the data to a CSV file
      filename = f"{self.symbol.replace('/','')}_{self.timeframe}_{start_date.strftime('%Y%m')}.csv"
      file_path = os.path.join(self.raw_path, filename)

      df.to_csv(file_path)

      print(f"Data saved to {filename}")

      # Increment the start date to the next month
      start_date = start_date.replace(day=1) + timedelta(days=32)
      start_date = start_date.replace(day=1)

  def get_data(self):
    # Obtener una lista de todos los archivos en la carpeta "data"
    data_files = os.listdir(self.raw_path)
    # Crear una lista vacía para almacenar los DataFrames de cada archivo
    data_frames = []

    # Cargar cada archivo CSV y agregar su DataFrame a la lista
    for file_name in data_files:
      if file_name.endswith(".csv"):
        file_path = os.path.join(self.raw_path, file_name)
        data = pd.read_csv(file_path, index_col=0, parse_dates=True)
        data_frames.append(data)

    # Concatenar los DataFrames en un solo DataFrame
    all_data = pd.concat(data_frames)
    return all_data

  def apply_filters(self,
                    data,
                    window_size=11,
                    polyorder=2,
                    kalman_observation_covariance=0.003,
                    kalman_transition_covariance=0.01,
                    kalman_initial_state_covariance=1000):

    # Aplicar suavizado exponencial
    alpha = 0.5
    data['close_ewm'] = data['close'].ewm(alpha=alpha, adjust=False).mean()

    # Aplicar filtro de Kalman
    kf = KalmanFilter(observation_covariance=kalman_observation_covariance,
                      transition_covariance=kalman_transition_covariance,
                      initial_state_covariance=kalman_initial_state_covariance,
                      n_dim_obs=1)
    data['close_kf'], _ = kf.filter(data['close'].values)

    # Aplicar suavizado de Savitzky-Golay
    data['close_savgol'] = savgol_filter(data['close'], window_size, polyorder)

    # Guardar los datos suavizados en un archivo CSV
    filename = f"{self.symbol.replace('/','')}_{self.timeframe}_{self.start_date.strftime('%Y%m')}_cleaned.csv"
    file_path = os.path.join(self.clean_path, filename)

    data.to_csv(file_path)

    return data