merge main + small changes

gamestonk_terminal/prediction_techniques/knn_view.py

@@ -63,7 +63,7 @@ def k_nearest_neighbors(other_args: List[str], s_ticker: str, df_stock: pd.DataF
         dest="n_inputs",
         type=check_positive,
         default=40,
-        help="number of days to use for prediction.",
+        help="number of days to use as input for prediction.",
     )
     parser.add_argument(
         "-d",
@@ -99,7 +99,16 @@ def k_nearest_neighbors(other_args: List[str], s_ticker: str, df_stock: pd.DataF
         type=valid_date,
         dest="s_end_date",
         default=None,
-        help="The end date (format YYYY-MM-DD) to select - Backtesting",
+        help="The end date (format YYYY-MM-DD) to select for testing",
+    )
+
+    parser.add_argument(
+        "-t",
+        "--test_size",
+        default = .2,
+        dest="test_size",
+        type = float,
+        help = "Percentage of data to validate in sample"
     )
 
     try:

gamestonk_terminal/prediction_techniques/neural_networks_helper.py

@@ -1,12 +0,0 @@
-"""Helper functions"""
-__docformat__ = "numpy"
-from typing import List, Tuple
-from datetime import datetime
-import pandas as pd
-import numpy as np
-from matplotlib import pyplot as plt
-from gamestonk_terminal.helper_funcs import (
-    get_next_stock_market_days,
-    patch_pandas_text_adjustment,
-    plot_autoscale,
-)

gamestonk_terminal/prediction_techniques/pred_helper.py

@@ -26,10 +26,12 @@ from gamestonk_terminal.config_plot import PLOT_DPI
 register_matplotlib_converters()
 
 
-def prepare_test_train_valid(
+def prepare_train_valid_test(
     df_stock, parsed_end_date, n_input_days, n_predict_days, test_size
 ):
 
+    df_test = df_stock[df_stock.index >= parsed_end_date]
+    df_stock = df_stock[df_stock.index < parsed_end_date]
     dates = df_stock.index
     prices = df_stock["5. adjusted close"].values
 
@@ -38,7 +40,12 @@ def prepare_test_train_valid(
     next_n_day_prices = []
     next_n_day_dates = []
 
+    test_days = []
+    test_inputs = []
+    test_next_n_days = []
+
     for idx in range(len(prices) - n_input_days - n_predict_days):
+
         input_prices.append(prices[idx : idx + n_input_days])
         input_dates.append(dates[idx : idx + n_input_days])
         next_n_day_prices.append(
@@ -55,13 +62,13 @@ def prepare_test_train_valid(
 
     (
         X_train,
-        X_test,
+        X_valid,
         y_train,
-        y_test,
+        y_valid,
         X_dates_train,
-        X_dates_test,
+        X_dates_valid,
         y_dates_train,
-        y_dates_test,
+        y_dates_valid,
     ) = train_test_split(
         input_prices,
         next_n_day_prices,
@@ -69,6 +76,16 @@ def prepare_test_train_valid(
         next_n_day_dates,
         test_size=test_size,
     )
+    return (
+        X_train,
+        X_valid,
+        y_train,
+        y_valid,
+        X_dates_train,
+        X_dates_valid,
+        y_dates_train,
+        y_dates_valid,
+    )
 
 
 def get_backtesting_data(