Added function to get all data and scale vs just a portion

compiler/characterizer/analytical_util.py

@@ -1,4 +1,12 @@
-#import diversipy as dp
+#
+# Copyright (c) 2016-2019 Regents of the University of California and The Board
+# of Regents for the Oklahoma Agricultural and Mechanical College
+# (acting for and on behalf of Oklahoma State University)
+# All rights reserved.
+#
+
+import debug
+
 import csv
 import math
 import numpy as np
@@ -131,6 +139,11 @@ def rescale_data(data, old_maxs, old_mins, new_maxs, new_mins):
     return data_new_scaling    
     
 def sample_from_file(num_samples, file_name, sample_dir=None):
+    """
+    Get a portion of the data from CSV file and scale it based on max/min of dataset.
+    Duplicate samples are trimmed.
+    """
+    
     if sample_dir:
         maxs,mins,avgs = get_max_min_from_datasets(sample_dir)
     else:
@@ -142,10 +155,7 @@ def sample_from_file(num_samples, file_name, sample_dir=None):
     # Get algorithms sample points, assuming hypercube for now
     num_labels = 1
     inp_dims = len(all_data) - num_labels
-    #samples = dp.hycusampling.lhd_matrix(num_samples, inp_dims)/num_samples
-    #samples = dp.hycusampling.halton(num_samples, inp_dims)
-    #samples = dp.hycusampling.random_uniform(num_samples, inp_dims)
-    samples = None
+    samples = np.random.rand(num_samples, inp_dims)
 
 
     # Scale data from file
@@ -169,6 +179,30 @@ def sample_from_file(num_samples, file_name, sample_dir=None):
         
     return np.asarray(sampled_data), np.asarray(unused_new_scaling)
 
+def get_scaled_data(file_name, sample_dir=None):
+    """Get data from CSV file and scale it based on max/min of dataset"""
+
+    if sample_dir:
+        maxs,mins,avgs = get_max_min_from_datasets(sample_dir)
+    else:
+        maxs,mins,avgs = [], [], []
+        
+    # Get data
+    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))
+
+    return np.asarray(self_scaled_data)
+
 def unscale_data(data, ref_dir, pos=None):
     if ref_dir:
         maxs,mins,avgs = get_max_min_from_datasets(ref_dir)

compiler/characterizer/lib.py

@@ -587,7 +587,11 @@ class lib:
         if self.use_model:
             #FIXME: ML models only designed for delay. Cannot produce all values for Lib
             d = linear_regression()
-            char_results = d.get_prediction()
+            model_inputs = [OPTS.num_words, 
+                            OPTS.word_size, 
+                            OPTS.words_per_row, 
+                            self.sram.width * self.sram.height]
+            char_results = d.get_prediction(model_inputs)
         
             #self.d = elmore(self.sram, self.sp_file, self.corner)
             # char_results = self.d.analytical_delay(self.slews,self.loads)

compiler/characterizer/linear_regression.py

@@ -19,13 +19,18 @@ data_dir = tech_path+'/'+OPTS.tech_name+relative_data_path
 
 class linear_regression():
 
-    def get_prediction(self):
+    def __init__(self):
+        self.model = None
+
+    def get_prediction(self, model_inputs):
 
         train_sets = []
         test_sets = []     
                
         file_path = data_dir +'/'+data_filename
-        num_points_train = 5
+        num_points_train = 7
+
+        samples = get_scaled_data(file_path, data_dir)
 
         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:]
@@ -46,7 +51,7 @@ class linear_regression():
                 new_error = self.run_model(train_x, train_y, test_x, test_y, data_dir)
                 debug.info(1, "Model Error: {}".format(new_error))
 
-    def run_model(x,y,test_x,test_y, reference_dir):
+    def train_model(self, x,y,test_x,test_y, reference_dir):
         model = LinearRegression()
         model.fit(x, y)
 
@@ -56,9 +61,9 @@ class linear_regression():
         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_error = abs_error(unscaled_labels, unscaled_preds)
-        max_error = max_error(unscaled_labels, unscaled_preds)
-        min_error = min_error(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_error, "max_error":max_error, "min_error":min_error}    
+        errors = {"avg_error": avg_err, "max_error":max_err, "min_error":min_err}    
         return errors