diff --git a/#tools.py# b/#tools.py#
new file mode 100644
index 0000000..5be273d
--- /dev/null
+++ b/#tools.py#
@@ -0,0 +1,153 @@
+from random import uniform
+from random import randint
+
+from numpy import array
+from numpy.linalg import pinv as pinv # pseudo inverse aka dagger
+from numpy import dot
+from numpy import eye
+from numpy import size
+
+def data_interval(low_b,high_b,N=100):
+    'returns a list of N values uniformly distributed between low boundary and high boundary'
+    d = []
+    for i in range(N):
+        d.append(uniform(low_b,high_b))
+    return d
+
+def data(N = 10):
+    'return N random points (x1,x2)'
+    d = []
+    for i in range(N):
+        x =  uniform(-1,1)
+        y =  uniform(-1,1)
+        d.append([x,y])
+    return d
+
+def data_from_file(filepath):
+    'from a filepath returns a dataset with the form [[x1,x2],y]'
+    datafile = open(filepath, 'r')
+    data = []
+    for line in datafile:
+        split = line.split()
+        x1 = float(split[0])
+        x2 = float(split[1])
+        y = float(split[2])
+        data.append([ [x1,x2],y ])
+    return data
+
+def randomline():
+    'computes a random line and returns [a,b] : y = ax + b'
+    x1 = uniform(-1,1)
+    y1 = uniform(-1,1)
+    x2 = uniform(-1,1)
+    y2 = uniform(-1,1)
+    
+    a = abs(x1-x2)/abs(y1-y2)
+    b = y1 - a*x1
+    return [a,b] # a*x + b
+
+def target_function(coords):
+    'from a coordinate input [a,b] returns the function a*x + b'
+    f = lambda x: coords[0]*x + coords[1]
+    return f
+
+def target_random_function(coords):
+    '''
+    description: from a coordinate (coords) with the format [a,b] generated a random function.
+    - coord: a list of the form [a,b]
+    - returns: the generated random function that takes as argument a list with the form [x,y]
+    and returns 1 or -1 whether y is below the linear function defined by a*x + b or above.
+    '''
+    func = target_function(coords)
+    def f(X):
+        x = X[0]
+        y = X[1]
+        if func(x) < y:
+            return 1.0
+        else:
+            return -1.0
+    return f
+
+def signex(x,compare_to = 0):
+    'returns +1 or -1 by comparing (x) to (compare_to) param (by default = 0)'
+    if x > compare_to:
+        return +1.
+    else:
+        return -1.
+
+def sign(x,compare_to = 0):
+    'returns +1 or -1 by comparing (x) to (compare_to) param (by default = 0)'
+    if x > compare_to:
+        return +1.
+    else:
+        return -1.
+
+def map_point(point,f):
+    'maps a point (x1,x2) to a sign -+1 following function f '
+    x1 = point[0]
+    y1 = point[1]
+    y = f(x1)
+    compare_to = y1
+    return sign(y,compare_to)
+
+def map_point_fmultipleparams(point,f):
+    y1 = point[1]
+    y = f(point)
+    compare_to = y1
+    return sign(y,compare_to)
+
+def build_training_set(data, func):
+    t_set = []
+    for i in range(len(data)):
+        point = data[i]
+        y = map_point(point,func)
+        t_set.append([ [ 1.0, point[0],point[1] ] , y ])
+    return t_set
+
+def build_training_set_fmultipleparams(data,func):
+    t_set = []
+    for i in range(len(data)):
+        point = data[i]
+        y = map_point_fmultipleparams(point,func)
+        t_set.append([ [ 1.0, point[0],point[1] ] , y ])
+    return t_set
+
+def print_avg(name,vector):
+    print 'Average %s: %s'%(name,sum(vector)/(len(vector)*1.0))
+
+def target_vector(t_set):
+    'creates a numpy array (eg a Y matrix) from the training set'
+    y = array([t[1] for t in t_set])
+    return y
+
+def input_data_matrix(t_set):
+    'creates a numpy array (eg a X matrix) from the training set'
+    X = array([t[0] for t in t_set])
+    return X
+
+def pseudo_inverse(X):
+    'dagger of pseudo matrix used for linear regression'
+    return pinv(X)
+
+def linear_regression(N_points,t_set):
+    '''Linear regresion algorithm
+    from Y and X compute the dagger or pseudo matrix
+    return the Xdagger.Y as the w vector
+    default lambda is 1.0
+    '''
+    y_vector = target_vector(t_set)
+    X_matrix = input_data_matrix(t_set)
+    X_pseudo_inverse = pseudo_inverse(X_matrix)
+    return dot(dot(X_pseudo_inverse,X_matrix.T),y_vector),X_matrix,y_vector
+
+def linear_regression_lda(N_points,t_set,lda):
+    '''Linear regresion algorithm
+    from Y and X compute the dagger or pseudo matrix
+    return the Xdagger.Y as the w vector
+    default lambda is 1.0
+    '''
+    y_vector = target_vector(t_set)
+    X_matrix = input_data_matrix(t_set)
+    X_pseudo_inverse = pseudo_inverse(dot(X_matrix.T,X_matrix)+lda*eye(size(X_matrix,1)))
+    return dot(dot(X_pseudo_inverse,X_matrix.T),y_vector),X_matrix,y_vector
+
diff --git a/.#tools.py b/.#tools.py
new file mode 120000
index 0000000..4f6cf56
--- /dev/null
+++ b/.#tools.py
@@ -0,0 +1 @@
+shino@macpro-santiago.lan.401
\ No newline at end of file
diff --git a/README.md b/README.md
index 1c75f01..1d474a5 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,59 @@
 caltech.ml
 ==========
 
-Machine learning course from Caltech
\ No newline at end of file
+Machine learning course from Caltech
+
+utils_data:
+-------------------------------------------------
+data_interval(low_b,high_b,N=100)
+rename with random_values(low_b,high_b,size)
+
+data(N = 10)
+rename with random_points(size)
+
+data_from_file(filepath)
+rename dataset_from_file
+
+build_training_set(data, func)
+rename build_dataset
+
+build_training_set_fmultipleparams(data,func)
+rename build_dataset_fmultiparams
+
+target_vector(t_set)
+rename target_vector(dataset)
+
+input_data_matrix(t_set)
+rename data_matrix(dataset)
+
+utils_math:
+------------------------------------------------
+randomline()
+rename random_line_coefs
+
+target_function(coords)
+rename linear_function(coefs)
+
+target_random_function(coords)
+rename random_function()...
+
+signex(x,compare_to = 0)
+delete use sign with an alias
+
+sign(x,compare_to = 0)
+map_point(point,f)
+rename get_sign(point,f)
+
+map_point_fmultipleparams(point,f)
+get_sign_multiparam
+
+pseudo_inverse(X)
+check if needed
+
+linear_regression(N_points,t_set,lda = 1.0)
+
+linear_regression_lda(N_points,t_set,lda)
+
+utils_print:
+-----------------------------------------------
+print_avg(name,vector)
\ No newline at end of file
diff --git a/hw1.py b/hw1.py
index 0de61f1..31230b1 100644
--- a/hw1.py
+++ b/hw1.py
@@ -106,7 +106,6 @@ def evaluate_diff_f_g(f,w):
         if sign_f != sign_g: diff = diff + 1
 
     return diff/(count*1.0)
-        
     
 def run_PLA(N_samples,N_points):
     samples = []# vector of 1 clasified, 0 misclassified
diff --git a/tools.py b/tools.py
index c992c1b..a81239b 100644
--- a/tools.py
+++ b/tools.py
@@ -130,7 +130,18 @@ def pseudo_inverse(X):
     'dagger of pseudo matrix used for linear regression'
     return pinv(X)
 
-def linear_regression(N_points,t_set,lda = 1.0):
+def linear_regression(N_points,t_set):
+    '''Linear regresion algorithm
+    from Y and X compute the dagger or pseudo matrix
+    return the Xdagger.Y as the w vector
+    default lambda is 1.0
+    '''
+    y_vector = target_vector(t_set)
+    X_matrix = input_data_matrix(t_set)
+    X_pseudo_inverse = pseudo_inverse(X_matrix)
+    return dot(dot(X_pseudo_inverse,X_matrix.T),y_vector),X_matrix,y_vector
+
+def linear_regression_lda(N_points,t_set,lda):
     '''Linear regresion algorithm
     from Y and X compute the dagger or pseudo matrix
     return the Xdagger.Y as the w vector
@@ -138,7 +149,6 @@ def linear_regression(N_points,t_set,lda = 1.0):
     '''
     y_vector = target_vector(t_set)
     X_matrix = input_data_matrix(t_set)
-    #X_pseudo_inverse = pseudo_inverse(X_matrix)#+lda*eye(size(X_matrix,0)))
     X_pseudo_inverse = pseudo_inverse(dot(X_matrix.T,X_matrix)+lda*eye(size(X_matrix,1)))
     return dot(dot(X_pseudo_inverse,X_matrix.T),y_vector),X_matrix,y_vector