From 6eccb6b26c094173587b3967d416300eee8f36a5 Mon Sep 17 00:00:00 2001
From: Michael Mutote <130656746+mr1Michael@users.noreply.github.com>
Date: Mon, 27 Nov 2023 11:34:55 +0100
Subject: [PATCH] 22202956 - optimised training supervised training
---
Reinforcement_Learning/Perceptrons.py | 47 +++++++--------
Reinforcement_Learning/Solution_Testing_1.py | 60 ++++++++++++--------
Reinforcement_Learning/Training_data.py | 5 +-
3 files changed, 58 insertions(+), 54 deletions(-)
diff --git a/Reinforcement_Learning/Perceptrons.py b/Reinforcement_Learning/Perceptrons.py
index a1ad48e..6767165 100644
--- a/Reinforcement_Learning/Perceptrons.py
+++ b/Reinforcement_Learning/Perceptrons.py
@@ -2,10 +2,13 @@ import numpy as np
import Training_data
rng = np.random.default_rng(123)
-TEACHDATA = 10000
-TESTDATA = 1000
-# ETA = 0.5
-T_NUMBER = 1 # Number to be detected 0-6
+TEACHDATA = 9999
+TESTDATA = 999
+
+T_NUMBER = 6 # Number to be detected 0-6
+
+test_data = Training_data.make_testset(TESTDATA, 0.3)
+teach_data = Training_data.make_testset(TEACHDATA, 0.2)
def sigmoid(val):
@@ -13,7 +16,6 @@ def sigmoid(val):
def linear_act(val):
-
# there is the option to make it linear in the valid range and make it constant otherwise
return val
@@ -23,21 +25,16 @@ def threshold(val):
class Neuron:
- test_data = Training_data.make_testset(TESTDATA)
- teach_data = Training_data.make_testset(TEACHDATA)
+
def __init__(self, input_count, activation):
self.input_count = input_count
self.activation = activation
self.weights = rng.random(input_count + 1)
- def test(self):
- res = [0 for _ in range(len(Neuron.test_data))]
- for number in range(len(Neuron.test_data)):
- for sample in Neuron.test_data[number]:
- ix = np.insert(sample.ravel(), 0, 1)
- res[number] = res[number] + (self.activation(ix.dot(self.weights)))
- return res
+ def test(self, data):
+ ix = np.insert(data.ravel(), 0, 1)
+ return self.activation(ix.dot(self.weights))
class ThresholdPerceptron(Neuron):
@@ -47,9 +44,9 @@ class ThresholdPerceptron(Neuron):
def train(self, ETA):
for i in range(TEACHDATA):
old_weights = np.copy(self.weights)
- for j in rng.permutation(len(Neuron.teach_data)):
+ for j in rng.permutation(len(teach_data)):
T = 1 if j == T_NUMBER else 0
- ix = np.insert(Neuron.teach_data[j][i].ravel(), 0, 1)
+ ix = np.insert(teach_data[j][i].ravel(), 0, 1)
RI = self.activation(ix.dot(self.weights))
if RI != T:
delta = ETA * \
@@ -65,17 +62,18 @@ class SGDPerceptron(Neuron):
super().__init__(input_count, activation)
def train(self, ETA):
-
for i in range(TEACHDATA):
old_weights = np.copy(self.weights)
delta = [0 for _ in range(len(old_weights))]
- for j in rng.choice(rng.permutation(len(Neuron.teach_data)),3):
+ for j in rng.choice(rng.permutation(len(teach_data)), 3):
T = (j == T_NUMBER)
- ix = np.insert(Neuron.teach_data[j][i].ravel(), 0, 1)
+ ix = np.insert(teach_data[j][i].ravel(), 0, 1)
z = ix.dot(self.weights)
RI = self.activation(z)
delta = ETA * (T - RI) * RI * (1 - RI) * ix
self.weights += delta
+ # if np.linalg.norm(old_weights - self.weights) == 0.00:
+ # return self.weights
return self.weights
@@ -87,14 +85,11 @@ class LinearPerceptron(Neuron):
for i in range(TEACHDATA):
old_weights = np.copy(self.weights)
delta = [0 for _ in range(len(old_weights))]
- for j in rng.permutation(len(Neuron.teach_data)):
+ for j in rng.permutation(len(teach_data)):
T = (j == T_NUMBER)
- ix = np.insert(Neuron.teach_data[j][i].ravel(), 0, 1)
+ ix = np.insert(teach_data[j][i].ravel(), 0, 1)
delta += ETA * (T - self.activation(ix.dot(self.weights))) * ix
self.weights = self.weights + delta
- if np.linalg.norm(old_weights - self.weights) == 0.00:
- return self.weights
+ # if np.linalg.norm(old_weights - self.weights) == 0.00:
+ # return self.weights
return self.weights
-
-
-
diff --git a/Reinforcement_Learning/Solution_Testing_1.py b/Reinforcement_Learning/Solution_Testing_1.py
index 0b07b7c..3e57838 100644
--- a/Reinforcement_Learning/Solution_Testing_1.py
+++ b/Reinforcement_Learning/Solution_Testing_1.py
@@ -1,29 +1,39 @@
import numpy as np
-
+from prettytable import PrettyTable
import Perceptrons
+# Define the table
+table = PrettyTable()
+
+
+trial_data = Perceptrons.test_data
+REPETION = 1
+
+
+def run_test(neuron, learning_rate):
+ global table
+ table = PrettyTable()
+ table.field_names = ["ETA", "0", "1", "2", "3", "4", "5", "6"]
+ for ETA in learning_rate: # the list of values for ETA
+ neuron.train(ETA)
+ res = [0] * len(trial_data)
+ for i, n_digits in enumerate(trial_data):
+ for trial_array in n_digits:
+ res[i] = res[i] + round(abs(neuron.test(trial_array)))
+ res = ["{:5d}".format(r) for r in res]
+ table.add_row([ETA] + res)
+ print(table)
+ return neuron
+
+for i in range(7):
+ Perceptrons.T_NUMBER = i
+ E = np.array([0.05, 0.1, 0.2, 0.4, 0.75, 1, 2, 5])
+ print("Threshold Perceptron is looking for: ", Perceptrons.T_NUMBER)
+ run_test(Perceptrons.ThresholdPerceptron(20), E/4)
+ print("Linear Perceptron is looking for: ", Perceptrons.T_NUMBER)
+ run_test(Perceptrons.LinearPerceptron(20), E / 160)
+ print("Sigmoid Gradient Descent Perceptron is looking for: ", Perceptrons.T_NUMBER)
+ x = run_test(Perceptrons.SGDPerceptron(20), E)
+
+
-def test_function(ETA, p):
- results = []
- output = np.round(p.test())
- results.append((ETA, output))
- return results
-
-
-for ETA in ([0.05, 0.1, 0.2, 0.4, 0.75, 1, 2, 5]): # the list of values for ETA
- w = Perceptrons.ThresholdPerceptron(20)
- w.train(ETA)
- x = Perceptrons.LinearPerceptron(20)
- x.train(ETA/200)
- y = Perceptrons.SGDPerceptron(20)
- y.train(ETA)
- for i in range(1):
- res = test_function(ETA, w)
- print("Thres", res) # print the results list
- for i in range(1):
- res = test_function(ETA/200, x)
- print("Lin", res) # print the results list
- for i in range(1):
- res = test_function(ETA, y)
- print("sgd", res) # print the results list
- print("\n\n")
diff --git a/Reinforcement_Learning/Training_data.py b/Reinforcement_Learning/Training_data.py
index 88da7d3..fc72a3a 100644
--- a/Reinforcement_Learning/Training_data.py
+++ b/Reinforcement_Learning/Training_data.py
@@ -1,6 +1,5 @@
import numpy as np
import copy
-
ideal = dict([])
ideal[0] = np.array([[0, 1, 1, 0],
@@ -46,7 +45,7 @@ ideal[6] = np.array([[0, 1, 1, 0],
[0, 1, 1, 0]])
-def make_testset(set_size):
+def make_testset(set_size, NOISE):
data = [[] for _ in range(len(ideal))]
rng = np.random.default_rng(123)
for number, value in ideal.items():
@@ -55,6 +54,6 @@ def make_testset(set_size):
for _ in range(set_size):
# scale is the standard deviation affecting the "spread" plays a role int eh results
# new_digit = ideal[number] + rng.normal(loc=0, scale=0.3, size=(5, 4))
- new_digit = ideal[number] + rng.normal(loc=0, scale=0.1, size=(5, 4))
+ new_digit = ideal[number] + rng.normal(loc=0, scale=NOISE, size=(5, 4))
data[number].append(new_digit)
return data
--
GitLab