add option to force single precision

freqtrade/freqai/data_kitchen.py

@@ -1246,6 +1246,9 @@ class FreqaiDataKitchen:
 
         self.get_unique_classes_from_labels(dataframe)
 
+        if self.freqai_config.get('convert_df_to_float32', False):
+            dataframe = self.reduce_dataframe_footprint(dataframe)
+
         return dataframe
 
     def fit_labels(self) -> None:
@@ -1344,3 +1347,35 @@ class FreqaiDataKitchen:
                 f"Could not find backtesting prediction file at {path_to_predictionfile}"
             )
             return False
+
+    def reduce_dataframe_footprint(self, df: DataFrame) -> DataFrame:
+        """
+        Ensure all values are float32
+        """
+        start_mem = df.memory_usage().sum() / 1024**2
+        print("Memory usage of dataframe is {:.2f} MB".format(start_mem))
+
+        for col in df.columns[1:]:
+            col_type = df[col].dtype
+
+            if col_type != object:
+                c_min = df[col].min()
+                c_max = df[col].max()
+                if str(col_type)[:3] == "int":
+                    if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:
+                        df[col] = df[col].astype(np.int8)
+                    elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:
+                        df[col] = df[col].astype(np.int16)
+                    elif c_min > np.iinfo(np.int32).min:
+                        df[col] = df[col].astype(np.int32)
+                else:
+                    if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:
+                        df[col] = df[col].astype(np.float16)
+                    elif c_min > np.finfo(np.float32).min:
+                        df[col] = df[col].astype(np.float32)
+
+        end_mem = df.memory_usage().sum() / 1024**2
+        print("Memory usage after optimization is: {:.2f} MB".format(end_mem))
+        print("Decreased by {:.1f}%".format(100 * (start_mem - end_mem) / start_mem))
+
+        return df