From 6bec719ce309378a7366ecceb70845bd7e1987eb Mon Sep 17 00:00:00 2001
From: mjjo <myeongjin_jo@solomonsc.com>
Date: Tue, 14 Aug 2018 17:22:50 +0900
Subject: [PATCH] =?UTF-8?q?=EC=88=98=EC=A0=95?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 regression2.py | 14 ++++++++------
 regressions.py |  3 ++-
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/regression2.py b/regression2.py
index 74df33c..e1e7ff3 100644
--- a/regression2.py
+++ b/regression2.py
@@ -6,15 +6,15 @@ import pandas as pd
 
 
 def load_data():
-	df = pd.read_csv('data/sample.txt', delimiter=',', header=None)
-	df[2] = pd.Series([1]*len(df[0]))
+	#df = pd.read_csv('data/sample.txt', delimiter=',', header=None)
+	#df[2] = pd.Series([1]*len(df[0]))
 
 	#df = pd.read_csv('data/ex1data1.txt', delimiter=',', header=None)
 	#df[2] = pd.Series([1]*len(df[0]))
 
-	#df = pd.read_csv('data/train.csv', delimiter=',', comment='#')
-	#df[0] = df['x']
-	#df[1] = df['y']
+	df = pd.read_csv('data/train.csv', delimiter=',', comment='#')
+	df[0] = df['x']
+	df[1] = df['y']
 
 	df[2] = pd.Series([1]*len(df[0]))
 	df = df.reindex(columns=[1, 2, 0])
@@ -23,8 +23,10 @@ def load_data():
 
 def feature_scaling(x):
 	mean = x.mean(0)
+	mean[0] = 0
 	std = x.std(0)
 	std[std==0] = 1
+	std[0] = 1
 	x = (x-mean)/std
 	return x, mean, std
 
@@ -40,7 +42,7 @@ x, mean, std = feature_scaling(x)
 
 sum_ = 0
 gap = 0.001
-break_gap = 1.0e-20
+break_gap = 1.0e-10
 trycnt = 0
 while True:
 	h = x@w
diff --git a/regressions.py b/regressions.py
index 30fd30f..04f7a4d 100644
--- a/regressions.py
+++ b/regressions.py
@@ -44,9 +44,10 @@ def get_derived_regularization_term(w: np.array, wlambda: float, alpha: float) -
 #	[5,15+1],
 #	])
 
+data = np.loadtxt('data/sample.txt', delimiter=',')
 #data = np.loadtxt('data/ex1data1.txt', delimiter=',')
 # train excercize
-data = np.loadtxt('data/train.csv', delimiter=',', skiprows=1, comments='#')
+#data = np.loadtxt('data/train.csv', delimiter=',', skiprows=1, comments='#')
 # auto mpg
 #df = pd.read_csv('data/auto-mpg.data', sep='\t')
 #df = df.drop(df.loc[df['horsepower'] == '?'].index)