rpuzonas/intelektikos-pagrindai
1
0
Fork 0
Code

lab3

Browse Source
This commit is contained in:
Rokas Puzonas 2024-05-13 01:32:51 +03:00
parent c86d4ca749
commit 19eaa28e47
4 changed files with 576 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
Ataskaita lab3.docx Normal file
View File

Binary file not shown.

212
lab3_1.py Normal file
View File

@ -0,0 +1,212 @@
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
from sklearn.linear_model import LinearRegression
import numpy as np
# Warning, this is not great code. Just something hacked together for the report.
def create_dataset(sunspots, n = 2):
P = []
T = []
for i in range(len(sunspots) - n):
P.append(np.array(sunspots["activity"][i:(i+n)]))
T.append(sunspots["activity"][i+n])
return P, T
# 1. & 2.
sunspots = pd.read_csv("sunspot.txt", delimiter='\t', header=None, names=["year", "activity"])
# 4.
if False:
plt.plot(sunspots['year'], sunspots["activity"])
plt.xlabel("Metai")
plt.ylabel("Aktyvumas")
plt.title(f"Saulės aktyvumas tarp {min(sunspots['year'])} ir {max(sunspots['year'])} metų")
plt.show()
# 5.
P, T = create_dataset(sunspots)
# 6.
def draw_scatterplot(Xs, Ys, marker = 'o'):
ax = plt.subplot(projection='3d')
X_coords = []
Y_coords = []
Z_coords = []
for i in range(len(Xs)):
X_coords.append(Xs[i][0])
Y_coords.append(Xs[i][1])
Z_coords.append(Ys[i])
ax.scatter(X_coords, Y_coords, Z_coords, marker=marker)
ax.set_xlabel('Užpraitų metų aktyvumas')
ax.set_ylabel('Praitų metų aktyvumas')
ax.set_zlabel('Šių metų aktyvumas')
ax.set_title('Šių metų aktyvumo priklausomybė nuo praėjusių metų')
return ax
if False:
draw_scatterplot(P, T)
plt.show()
# 7.
assert len(P) > 200
Pu = P[:200]
Tu = T[:200]
# 8.
model = LinearRegression().fit(Pu, Tu)
# 9.
print(f"intercept: {model.intercept_}")
print(f"coefficients: {model.coef_}")
if False:
w1 = model.coef_[0]
w2 = model.coef_[1]
b = model.intercept_
x1 = max(p[0] for p in P)
x2 = max(p[1] for p in P)
ax = draw_scatterplot(P, T)
ax.plot([0, x1], [0, x2], 'r', zs=[b, x1*w1 + x2*w2 + b])
plt.show()
# 10.
if False:
draw_scatterplot(Pu, model.predict(Pu))
draw_scatterplot(Pu, Tu)
plt.legend(handles=[
mpatches.Patch(color='blue', label='Tikrasis'),
mpatches.Patch(color='orange', label='Numatytas')
])
plt.show()
# 11.
if False:
e = np.array(Tu) - model.predict(Pu)
draw_scatterplot(Pu, e)
plt.show()
# 12.
if False:
e = np.array(Tu) - model.predict(Pu)
plt.hist(e, bins=40)
plt.xlabel("Klaida")
plt.ylabel("Dažnis")
plt.show()
# 13.
e = np.array(Tu) - model.predict(Pu)
print("MSE (train)", np.sum(e**2) / len(e))
print("MAD (train)", np.median(np.abs(e)))
e = np.array(T[200:]) - model.predict(P[200:])
print("MSE (test)", np.sum(e**2) / len(e))
print("MAD (test)", np.median(np.abs(e)))
# 14. & 15. & 16.
class AdaptiveLinearNeuron(object):
def __init__(self, rate = 0.01, max_niter = 10, mse_goal = -1):
self.rate = rate
self.max_niter = max_niter
self.mse_goal = mse_goal
def fit(self, X, y):
"""Fit training data
X : Training vectors, X.shape : [#samples, #features]
y : Target values, y.shape : [#samples]
"""
# weights
self.weight = np.zeros(1 + X.shape[1])
# Number of misclassifications
self.errors = []
# Cost function
self.cost = []
for i in range(self.max_niter):
output = self.net_input(X)
errors = y - output
self.weight[1:] += self.rate * X.T.dot(errors)
self.weight[0] += self.rate * errors.sum()
cost = (errors**2).sum() / 2.0
self.cost.append(cost)
mse = np.average(errors**2)
if self.mse_goal != -1 and mse < self.mse_goal: break
return self
def net_input(self, X):
"""Calculate net input"""
return np.dot(X, self.weight[1:]) + self.weight[0]
def activation(self, X):
"""Compute linear activation"""
return self.net_input(X)
def predict(self, X):
"""Return class label after unit step"""
return np.where(self.activation(X) >= 0.0, 1, -1)
# print("---------------")
# for lr in [5e-5, 1e-5, 5e-6, 1e-6, 5e-7, 1e-7, 5e-8, 1e-8, 5e-9, 1e-9]:
# aln = AdaptiveLinearNeuron(lr, 100000, 300).fit(np.array(Pu), np.array(Tu))
# print(lr, aln.cost[-1], len(aln.cost))
print("---------------")
aln = AdaptiveLinearNeuron(0.000001, 1000, 280).fit(np.array(Pu), np.array(Tu))
if False:
plt.plot(aln.cost, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Sum-squared-error')
plt.title('Adaptive Linear Neuron - Learning rate 0.000001')
plt.show()
# 17.
print("iterations", len(aln.cost))
print("b", aln.weight[0])
print("w1", aln.weight[1])
print("w2", aln.weight[2])
# 18.
# * Taip konverguoja, nes pasiekiama užsibrėžta MSE riba
# * b ~ 0.17, w1 ~ -0.58, w2 ~ 1.46
# 19.
# Didinti 'lr' nelabai galima, nes tada pradės nekonverguoti ir įvyks slankaus kablelio klaidos
# Mažinant 'lr' tiesiog prailgina mokymosi ilgiai tiesiškai
# 20.
print("------ Didinimas ---------")
for n in [2, 4, 6, 8, 10]:
print(f"====== n = {n}")
P, T = create_dataset(sunspots, n)
assert len(P) > 200
Pu = np.array(P[:200])
Tu = np.array(T[:200])
# aln = AdaptiveLinearNeuron(1e-7, 1000).fit(Pu, Tu)
# plt.plot(aln.cost, marker='o')
# plt.xlabel('Epochs')
# plt.ylabel('Sum-squared-error')
# plt.title('Adaptive Linear Neuron - Learning rate 0.000001')
# plt.show()
# print(f"cost (n={n}) ", aln.cost[-1])
# print(f"iterations (n={n}) ", len(aln.cost))
model = LinearRegression().fit(Pu, Tu)
e = Tu - model.predict(Pu)
print("MSE (train)", np.average(e**2))
print("MAD (train)", np.median(np.abs(e)))
e = np.array(T[200:]) - model.predict(P[200:])
print("MSE (test)", np.average(e**2))
print("MAD (test)", np.median(np.abs(e)))

49
lab3_2.py Normal file
View File

@ -0,0 +1,49 @@
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf
from sklearn.model_selection import cross_val_score
def load_data():
apples = pd.read_csv("apple_quality_clean.csv")
return apples.drop(columns=["Quality"]), apples["Quality"]
X, Y = load_data()
# Convert values from a 0..1 range to a (-1)..1 range
# Conclusion: makes no difference
#X = X.map(lambda x: x*2 - 1)
tf.keras.utils.set_random_seed(42)
model = tf.keras.models.Sequential([
tf.keras.layers.Dense(1, activation='relu')
])
model.build(input_shape=[None,len(X.columns)])
model.compile(
optimizer=tf.keras.optimizers.Adam(learning_rate=0.01),
loss='binary_crossentropy',
metrics=['accuracy'],
)
history = model.fit(
X,
Y,
batch_size=len(X),
epochs=200,
shuffle=True,
validation_split=0.2
)
# print("10-fold cross validation score:", cross_val_score(model, X, Y, cv=10))
# print("Accuracy", history.history['acc'][-1])
# print(model.score)
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.xlabel('Iterations')
plt.ylabel('accuracy')
plt.show()

315
sunspot.txt Normal file
View File

@ -0,0 +1,315 @@
1700 5
1701 11
1702 16
1703 23
1704 36
1705 58
1706 29
1707 20
1708 10
1709 8
1710 3
1711 0
1712 0
1713 2
1714 11
1715 27
1716 47
1717 63
1718 60
1719 39
1720 28
1721 26
1722 22
1723 11
1724 21
1725 40
1726 78
1727 122
1728 103
1729 73
1730 47
1731 35
1732 11
1733 5
1734 16
1735 34
1736 70
1737 81
1738 111
1739 101
1740 73
1741 40
1742 20
1743 16
1744 5
1745 11
1746 22
1747 40
1748 60
1749 81
1750 83
1751 48
1752 48
1753 31
1754 12
1755 10
1756 10
1757 32
1758 48
1759 54
1760 63
1761 86
1762 61
1763 45
1764 36
1765 21
1766 11
1767 38
1768 70
1769 106
1770 101
1771 82
1772 67
1773 35
1774 31
1775 7
1776 20
1777 93
1778 154
1779 126
1780 85
1781 68
1782 39
1783 23
1784 10
1785 24
1786 83
1787 132
1788 131
1789 118
1790 90
1791 67
1792 60
1793 47
1794 41
1795 21
1796 16
1797 6
1798 4
1799 7
1800 15
1801 34
1802 45
1803 43
1804 48
1805 42
1806 28
1807 10
1808 8
1809 3
1810 0
1811 1
1812 5
1813 12
1814 14
1815 35
1816 46
1817 41
1818 30
1819 24
1820 16
1821 7
1822 4
1823 2
1824 9
1825 17
1826 36
1827 50
1828 64
1829 67
1830 71
1831 48
1832 28
1833 9
1834 13
1835 57
1836 122
1837 138
1838 103
1839 86
1840 65
1841 37
1842 24
1843 11
1844 15
1845 40
1846 62
1847 99
1848 125
1849 96
1850 67
1851 65
1852 54
1853 39
1854 21
1855 7
1856 4
1857 23
1858 55
1859 94
1860 96
1861 77
1862 59
1863 44
1864 47
1865 31
1866 16
1867 7
1868 38
1869 74
1870 139
1871 111
1872 102
1873 66
1874 45
1875 17
1876 11
1877 12
1878 3
1879 6
1880 32
1881 54
1882 60
1883 64
1884 64
1885 52
1886 25
1887 13
1888 7
1889 6
1890 7
1891 36
1892 73
1893 85
1894 78
1895 64
1896 42
1897 26
1898 27
1899 12
1900 10
1901 3
1902 5
1903 24
1904 42
1905 64
1906 54
1907 62
1908 49
1909 44
1910 19
1911 6
1912 4
1913 1
1914 10
1915 47
1916 57
1917 104
1918 81
1919 64
1920 38
1921 26
1922 14
1923 6
1924 17
1925 44
1926 64
1927 69
1928 78
1929 65
1930 36
1931 21
1932 11
1933 6
1934 9
1935 36
1936 80
1937 114
1938 110
1939 89
1940 68
1941 48
1942 31
1943 16
1944 10
1945 33
1946 93
1947 152
1948 136
1949 135
1950 84
1951 69
1952 32
1953 14
1954 4
1955 38
1956 142
1957 190
1958 185
1959 159
1960 112
1961 54
1962 38
1963 28
1964 10
1965 15
1966 47
1967 94
1968 106
1969 106
1970 105
1971 67
1972 69
1973 38
1974 35
1975 16
1976 13
1977 28
1978 93
1979 155
1980 155
1981 141
1982 116
1983 67
1984 46
1985 18
1986 13
1987 29
1988 100
1989 158
1990 143
1991 146
1992 94
1993 55
1994 30
1995 18
1996 9
1997 22
1998 64
1999 93
2000 119
2001 111
2002 104
2003 64
2004 40
2005 30
2006 15
2007 7
2008 3
2009 4
2010 16
2011 57
2012 58
2013 65
2014 79