From 110631594b4f79548be6a32c081494d542b695d8 Mon Sep 17 00:00:00 2001
From: snsd0805 <levi900227@gmail.com>
Date: Wed, 15 Nov 2023 20:44:06 +0800
Subject: [PATCH] fix: add feature transform

---
 hw4/hw4_10.py | 26 ++++++++++++++++++++++++++
 hw4/hw4_11.py | 30 ++++++++++++++++++++++++++++--
 hw4/hw4_12.py | 26 ++++++++++++++++++++++++++
 3 files changed, 80 insertions(+), 2 deletions(-)

diff --git a/hw4/hw4_10.py b/hw4/hw4_10.py
index 38c0fa3..23bcdf7 100644
--- a/hw4/hw4_10.py
+++ b/hw4/hw4_10.py
@@ -33,7 +33,33 @@ def error(gt, pred):
         err = (err+1) if gt[index]!=pred[index] else err
     return err/len(gt)
 
+def transform(features):
+    output_features = []
+    for index, feature in enumerate(features):
+        output_features.append([ 0 for _ in range(84) ])
+        output_features[index][0] = 1
+        
+        d_index = 1   
+        # 1-order
+        for i in feature:
+            output_features[index][d_index] = i
+            d_index += 1
+    
+        # 2-orde
+        for i in range(len(feature)):
+            for j in range(i, len(feature)):
+                output_features[index][d_index] = feature[i]*feature[j]
+                d_index += 1
+        # 3-order
+        for i in range(len(feature)):
+            for j in range(i, len(feature)):
+                for k in range(j, len(feature)):
+                    output_features[index][d_index] = i*j*k
+                    d_index += 1
+    return output_features
+
 x, y = read_data(FILENAME)
+x = transform(x)
 x = format(x)
 prob = problem(y, x)
 lambda_powers = [-6, -4, -2, 0, 2]
diff --git a/hw4/hw4_11.py b/hw4/hw4_11.py
index 1eacc73..ce52017 100644
--- a/hw4/hw4_11.py
+++ b/hw4/hw4_11.py
@@ -36,7 +36,6 @@ def error(gt, pred):
     return err/len(gt)
 
 def new_split(x, y):
-    random.seed(datetime.datetime.now().timestamp())
     data = list(zip(x, y))
     random.shuffle(data)
     x, y = zip(*data)
@@ -44,10 +43,37 @@ def new_split(x, y):
     train_y, val_y = y[:120], y[120:]
     return (train_x, train_y), (val_x, val_y)
 
+def transform(features):
+    output_features = []
+    for index, feature in enumerate(features):
+        output_features.append([ 0 for _ in range(84) ])
+        output_features[index][0] = 1
+        
+        d_index = 1   
+        # 1-order
+        for i in feature:
+            output_features[index][d_index] = i
+            d_index += 1
+    
+        # 2-orde
+        for i in range(len(feature)):
+            for j in range(i, len(feature)):
+                output_features[index][d_index] = feature[i]*feature[j]
+                d_index += 1
+        # 3-order
+        for i in range(len(feature)):
+            for j in range(i, len(feature)):
+                for k in range(j, len(feature)):
+                    output_features[index][d_index] = i*j*k
+                    d_index += 1
+    return output_features
+
 x, y = read_data(FILENAME)
+x = transform(x)
 x = format(x)
 log_lambda = []
-for _ in range(128):
+for index in range(128):
+    random.seed(datetime.datetime.now().timestamp()+index)
     (train_x, train_y), (val_x, val_y) = new_split(x, y)
     prob = problem(train_y, train_x)
 
diff --git a/hw4/hw4_12.py b/hw4/hw4_12.py
index edb45e9..59f69ec 100644
--- a/hw4/hw4_12.py
+++ b/hw4/hw4_12.py
@@ -52,7 +52,33 @@ def new_split(x, y):
 
     return folds
 
+def transform(features):
+    output_features = []
+    for index, feature in enumerate(features):
+        output_features.append([ 0 for _ in range(84) ])
+        output_features[index][0] = 1
+        
+        d_index = 1   
+        # 1-order
+        for i in feature:
+            output_features[index][d_index] = i
+            d_index += 1
+    
+        # 2-orde
+        for i in range(len(feature)):
+            for j in range(i, len(feature)):
+                output_features[index][d_index] = feature[i]*feature[j]
+                d_index += 1
+        # 3-order
+        for i in range(len(feature)):
+            for j in range(i, len(feature)):
+                for k in range(j, len(feature)):
+                    output_features[index][d_index] = i*j*k
+                    d_index += 1
+    return output_features
+
 x, y = read_data(FILENAME)
+x = transform(x)
 x = format(x)
 log_lambda = []
 lambda_powers = [-6, -4, -2, 0, 2]