fix timestamping, move imports, add words to doc

docs/freqai.md

@@ -116,7 +116,7 @@ Mandatory parameters are marked as **Required**, which means that they are requi
 | `outlier_protection_percentage` | If more than `outlier_protection_percentage` fraction of points are removed as outliers, FreqAI will log a warning message and ignore outlier detection while keeping the original dataset intact. <br> **Datatype:** float. Default: `30`
 | `reverse_train_test_order` | If true, FreqAI will train on the latest data split and test on historical split of the data. This allows the model to be trained up to the most recent data point, while avoiding overfitting. However, users should be careful to understand unorthodox nature of this parameter before employing it. <br> **Datatype:** bool. Default: False
 | `inlier_metric_window` | If set, FreqAI will add the `inlier_metric` to the training feature set and set the lookback to be the `inlier_metric_window`. Details of how the `inlier_metric` is computed can be found [here](#using-the-inliermetric) <br> **Datatype:** int. Default: 0
-| `noise_standard_deviation` | If > 0, FreqAI adds noise to the training features. FreqAI generates random deviates from a gaussian distribution with a standard deviation of `noise_standard_deviation` and adds them to all data points. Value should be kept relative to the normalized space between -1 and 1). In other words, since data is always normalized between -1 and 1 in FreqAI, the user can expect a `noise_standard_deviation: 0.05` to see 32% of data randomly increased/decreased by more than 2.5%. Good for preventing overfitting. <br> **Datatype:** int. Default: 0
+| `noise_standard_deviation` | If > 0, FreqAI adds noise to the training features. FreqAI generates random deviates from a gaussian distribution with a standard deviation of `noise_standard_deviation` and adds them to all data points. Value should be kept relative to the normalized space between -1 and 1). In other words, since data is always normalized between -1 and 1 in FreqAI, the user can expect a `noise_standard_deviation: 0.05` to see 32% of data randomly increased/decreased by more than 2.5% (i.e. the percent of data falling within the first standard deviation). Good for preventing overfitting. <br> **Datatype:** int. Default: 0
 |  |  **Data split parameters**
 | `data_split_parameters` | Include any additional parameters available from Scikit-learn `test_train_split()`, which are shown [here](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website). <br> **Datatype:** Dictionary.
 | `test_size` | Fraction of data that should be used for testing instead of training. <br> **Datatype:** Positive float < 1.

freqtrade/freqai/data_kitchen.py

@@ -2,12 +2,14 @@ import copy
 import logging
 import shutil
 from datetime import datetime, timezone
+from math import cos, sin
 from pathlib import Path
 from typing import Any, Dict, List, Tuple
 
 import numpy as np
 import numpy.typing as npt
 import pandas as pd
+import scipy.stats as stats
 from pandas import DataFrame
 from sklearn import linear_model
 from sklearn.cluster import DBSCAN
@@ -401,8 +403,8 @@ class FreqaiDataKitchen:
             timerange_train.stopts = timerange_train.startts + train_period_days
 
             first = False
-            start = datetime.utcfromtimestamp(timerange_train.startts)
+            start = datetime.fromtimestamp(timerange_train.startts, tz=timezone.utc)
-            stop = datetime.utcfromtimestamp(timerange_train.stopts)
+            stop = datetime.fromtimestamp(timerange_train.stopts, tz=timezone.utc)
             tr_training_list.append(start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d"))
             tr_training_list_timerange.append(copy.deepcopy(timerange_train))
 
@@ -415,8 +417,8 @@ class FreqaiDataKitchen:
             if timerange_backtest.stopts > config_timerange.stopts:
                 timerange_backtest.stopts = config_timerange.stopts
 
-            start = datetime.utcfromtimestamp(timerange_backtest.startts)
+            start = datetime.fromtimestamp(timerange_backtest.startts, tz=timezone.utc)
-            stop = datetime.utcfromtimestamp(timerange_backtest.stopts)
+            stop = datetime.fromtimestamp(timerange_backtest.stopts, tz=timezone.utc)
             tr_backtesting_list.append(start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d"))
             tr_backtesting_list_timerange.append(copy.deepcopy(timerange_backtest))
 
@@ -630,8 +632,6 @@ class FreqaiDataKitchen:
         is an outlier.
         """
 
-        from math import cos, sin
-
         if predict:
             if not self.data['DBSCAN_eps']:
                 return
@@ -732,8 +732,6 @@ class FreqaiDataKitchen:
         into previous timepoints.
         """
 
-        import scipy.stats as ss
-
         no_prev_pts = self.freqai_config["feature_parameters"]["inlier_metric_window"]
 
         if set_ == 'train':
@@ -778,8 +776,8 @@ class FreqaiDataKitchen:
         inliers = pd.DataFrame(index=distances.index)
         for key in distances.keys():
             current_distances = distances[key].dropna()
-            fit_params = ss.weibull_min.fit(current_distances)
+            fit_params = stats.weibull_min.fit(current_distances)
-            quantiles = ss.weibull_min.cdf(current_distances, *fit_params)
+            quantiles = stats.weibull_min.cdf(current_distances, *fit_params)
 
             df_inlier = pd.DataFrame(
                 {key: quantiles}, index=distances.index
@@ -794,8 +792,8 @@ class FreqaiDataKitchen:
             index=compute_df.index
         )
 
-        inlier_metric = 2 * (inlier_metric - inlier_metric.min()) / \
+        inlier_metric = (2 * (inlier_metric - inlier_metric.min()) /
-            (inlier_metric.max() - inlier_metric.min()) - 1
+                         (inlier_metric.max() - inlier_metric.min()) - 1)
 
         if set_ in ('train', 'test'):
             inlier_metric = inlier_metric.iloc[no_prev_pts:]
@@ -956,8 +954,8 @@ class FreqaiDataKitchen:
         backtest_timerange.startts = (
             backtest_timerange.startts - backtest_period_days * SECONDS_IN_DAY
         )
-        start = datetime.utcfromtimestamp(backtest_timerange.startts)
+        start = datetime.fromtimestamp(backtest_timerange.startts, tz=timezone.utc)
-        stop = datetime.utcfromtimestamp(backtest_timerange.stopts)
+        stop = datetime.fromtimestamp(backtest_timerange.stopts, tz=timezone.utc)
         full_timerange = start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d")
 
         self.full_path = Path(

freqtrade/freqai/freqai_interface.py

@@ -1,10 +1,9 @@
-# import contextlib
 import logging
 import shutil
 import threading
 import time
 from abc import ABC, abstractmethod
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from threading import Lock
 from typing import Any, Dict, Tuple
@@ -214,12 +213,12 @@ class IFreqaiModel(ABC):
             dataframe_backtest = dk.slice_dataframe(tr_backtest, dataframe)
 
             trained_timestamp = tr_train
-            tr_train_startts_str = datetime.utcfromtimestamp(tr_train.startts).strftime(
+            tr_train_startts_str = datetime.fromtimestamp(
-                "%Y-%m-%d %H:%M:%S"
+                                                tr_train.startts,
-            )
+                                                tz=timezone.utc).strftime("%Y-%m-%d %H:%M:%S")
-            tr_train_stopts_str = datetime.utcfromtimestamp(tr_train.stopts).strftime(
+            tr_train_stopts_str = datetime.fromtimestamp(
-                "%Y-%m-%d %H:%M:%S"
+                                                tr_train.stopts,
-            )
+                                                tz=timezone.utc).strftime("%Y-%m-%d %H:%M:%S")
             logger.info(
                 f"Training {metadata['pair']}, {self.pair_it}/{self.total_pairs} pairs"
                 f" from {tr_train_startts_str} to {tr_train_stopts_str}, {train_it}/{total_trains} "

tests/freqai/conftest.py

@@ -93,12 +93,11 @@ def make_unfiltered_dataframe(mocker, freqai_conf):
     freqai.live = True
     freqai.dk = FreqaiDataKitchen(freqai_conf)
     freqai.dk.pair = "ADA/BTC"
-    timerange = TimeRange.parse_timerange("20180110-20180130")
+    data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
-    freqai.dd.load_all_pair_histories(timerange, freqai.dk)
+    freqai.dd.load_all_pair_histories(data_load_timerange, freqai.dk)
 
     freqai.dd.pair_dict = MagicMock()
-
+ 
-    data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
     new_timerange = TimeRange.parse_timerange("20180120-20180130")
 
     corr_dataframes, base_dataframes = freqai.dd.get_base_and_corr_dataframes(
@@ -125,12 +124,11 @@ def make_data_dictionary(mocker, freqai_conf):
     freqai.live = True
     freqai.dk = FreqaiDataKitchen(freqai_conf)
     freqai.dk.pair = "ADA/BTC"
-    timerange = TimeRange.parse_timerange("20180110-20180130")
+    data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
-    freqai.dd.load_all_pair_histories(timerange, freqai.dk)
+    freqai.dd.load_all_pair_histories(data_load_timerange, freqai.dk)
 
     freqai.dd.pair_dict = MagicMock()
 
-    data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
     new_timerange = TimeRange.parse_timerange("20180120-20180130")
 
     corr_dataframes, base_dataframes = freqai.dd.get_base_and_corr_dataframes(