added normalisation with dictionnary

skais/ais/ais_trajectory.py

@@ -224,8 +224,22 @@ class AISTrajectory:
         l2 = l2_angle(dat, radius)
         self.df[f"angle_l2"] = l2
 
-    def normalize(self, features, normalization_type="min-max"):
-        normalization_dict = {}
+    def normalize(self, features, normalization_type="min-max", dictionary=None):
+        normalization_dict = None
+        if dictionary is not None:
+            if dictionary["type"] == "min-max":
+                for f in features:
+                    minimum = dictionary[f"{f}_minimum"]
+                    maximum = dictionary[f"{f}_maximum"]
+                    self.df[f] = (self.df[f] - minimum) / (maximum - minimum)
+
+            elif dictionary["type"] == "standardization":
+                for f in features:
+                    mean = dictionary[f"{f}_mean"]
+                    std = dictionary[f"{f}_std"]
+                    self.df[f] = (self.df[f] - mean) / std
+        else:
+            normalization_dict = {"type": normalization_type}
             if normalization_type == "min-max":
                 for f in features:
                     minimum = self.df[f].min()
@@ -235,7 +249,6 @@ class AISTrajectory:
                     normalization_dict[f"{f}_maximum"] = maximum
 
             elif normalization_type == "standardization":
-            normalisation_factors = ("standardization", {})
                 for f in features:
                     mean = self.df[f].mean()
                     std = self.df[f].std()
@@ -249,7 +262,8 @@ class AISTrajectory:
             else:
                 raise ValueError(f"{normalization_type} not a valid normalization method. Must be on of [min-max, "
                                  f"standardization]")
-        return normalization_type, normalization_dict
+
+        return normalization_dict
 
     def compute_derivative(self, field):
         dt = self.df['ts_sec'].diff() / 60

skais/utils/experiment_tools.py

@@ -9,6 +9,7 @@ def make_feature_vectors(trajectories, features=None,
     zero = [0 for _ in range(nb_classes)]
 
     for trajectory in trajectories:
+        trajectory.df.dropna(inplace=True)
         if len(trajectory.df.index) > length_list:
             trajectory.df['ts'] = trajectory.df.index
             trajectory.compute_all_derivatives()