From 6e7d1695b51087c793905d1569fc7cecb1c7dbfe Mon Sep 17 00:00:00 2001
From: Hunter Nichols <hznichol@ucsc.edu>
Date: Mon, 7 Dec 2020 14:22:53 -0800
Subject: [PATCH] Cleaned code to remove validation during training.

---
 compiler/characterizer/analytical_util.py   | 42 ++++++++++----
 compiler/characterizer/linear_regression.py | 62 +++++++++------------
 2 files changed, 57 insertions(+), 47 deletions(-)

diff --git a/compiler/characterizer/analytical_util.py b/compiler/characterizer/analytical_util.py
index b93f463d..e09a1bba 100644
--- a/compiler/characterizer/analytical_util.py
+++ b/compiler/characterizer/analytical_util.py
@@ -191,17 +191,39 @@ def get_scaled_data(file_name, sample_dir=None):
     all_data = get_data(file_name)  
     
     # Data is scaled by max/min and data format is changed to points vs feature lists
-    self_scaled_data = [[] for _ in range(len(all_data[0]))]
-    self_maxs,self_mins = [],[]
-    for feature_list in all_data:
-        max_val = max(feature_list)
-        self_maxs.append(max_val)
-        min_val = min(feature_list)
-        self_mins.append(min_val)
-        for i in range(len(feature_list)):
-            self_scaled_data[i].append((feature_list[i]-min_val)/(max_val-min_val))
+    self_scaled_data = scale_data_and_transform(all_data)
 
-    return np.asarray(self_scaled_data)
+    samples = np.asarray(self_scaled_data)
+    features, labels = samples[:, :-1], samples[:,-1:]
+    return features, labels
+
+def scale_data_and_transform(data):
+    """
+    Assume data is a list of features, change to a list of points and max/min scale
+    """
+    
+    scaled_data = [[] for _ in range(len(data[0]))]
+    for feature_list in data:
+        max_val = max(feature_list)
+        min_val = min(feature_list)
+        for i in range(len(feature_list)):
+            scaled_data[i].append((feature_list[i]-min_val)/(max_val-min_val))
+    return scaled_data
+    
+def scale_input_datapoint(point, data_dir):    
+    """
+    Input data has no output and needs to be scaled like the model inputs during
+    training.
+    """
+    maxs, mins, avgs = get_max_min_from_datasets(data_dir)
+    debug.info(1, "maxs={}".format(maxs))
+    debug.info(1, "mins={}".format(mins))
+    debug.info(1, "point={}".format(point))
+
+    scaled_point = []
+    for feature, mx, mn in zip(point, maxs, mins):
+        scaled_point.append((feature-mn)/(mx-mn))
+    return scaled_point
 
 def unscale_data(data, ref_dir, pos=None):
     if ref_dir:
diff --git a/compiler/characterizer/linear_regression.py b/compiler/characterizer/linear_regression.py
index 8c69f6be..897ad54b 100644
--- a/compiler/characterizer/linear_regression.py
+++ b/compiler/characterizer/linear_regression.py
@@ -28,42 +28,30 @@ class linear_regression():
         test_sets = []     
                
         file_path = data_dir +'/'+data_filename
-        num_points_train = 7
+        scaled_inputs = np.asarray(scale_input_datapoint(model_inputs, data_dir))
 
-        samples = get_scaled_data(file_path, data_dir)
+        features, labels = get_scaled_data(file_path, data_dir)
+        self.train_model(features, labels)
+        scaled_pred = model_prediction(model_inputs)
+        pred = unscale_data(scaled_pred.tolist(), data_dir)
+        debug.info(1,"Unscaled Prediction = {}".format(pred))
+        return pred
 
-        non_ip_samples, unused_samples = sample_from_file(num_points_train, file_path, data_dir)
-        nip_features_subset, nip_labels_subset = non_ip_samples[:, :-1], non_ip_samples[:,-1:]
-        nip_test_feature_subset, nip_test_labels_subset = unused_samples[:, :-1], unused_samples[:,-1:]
-
-        train_sets = [(nip_features_subset, nip_labels_subset)]
-        test_sets = [(nip_test_feature_subset, nip_test_labels_subset)]
-
-        runs_per_model = 1
-
-        for train_tuple, test_tuple in zip(train_sets, test_sets):
-            train_x, train_y = train_tuple
-            test_x, test_y = test_tuple
-
-            errors = {}
-            min_train_set = None
-            for _ in range(runs_per_model):
-                new_error = self.run_model(train_x, train_y, test_x, test_y, data_dir)
-                debug.info(1, "Model Error: {}".format(new_error))
-
-    def train_model(self, x,y,test_x,test_y, reference_dir):
-        model = LinearRegression()
-        model.fit(x, y)
-
-        pred = model.predict(test_x)
-
-        #print(pred)
-        unscaled_labels = unscale_data(test_y.tolist(), reference_dir)
-        unscaled_preds = unscale_data(pred.tolist(), reference_dir)
-        unscaled_labels, unscaled_preds = (list(t) for t in zip(*sorted(zip(unscaled_labels, unscaled_preds))))
-        avg_err = abs_error(unscaled_labels, unscaled_preds)
-        max_err = max_error(unscaled_labels, unscaled_preds)
-        min_err = min_error(unscaled_labels, unscaled_preds)
-
-        errors = {"avg_error": avg_err, "max_error":max_err, "min_error":min_err}    
-        return errors
\ No newline at end of file
+    def train_model(self, features, labels):
+        """
+        Supervised training of model.
+        """
+        
+        self.model = LinearRegression()
+        self.model.fit(features, labels)
+        
+    def model_prediction(self, features):    
+        """
+        Have the model perform a prediction and unscale the prediction
+        as the model is trained with scaled values.
+        """
+        
+        pred = self.model.predict(features)
+        debug.info(1, "pred={}".format(pred))
+        return pred
+        
\ No newline at end of file