première version des TP
這個提交存在於：
Farina Louis
父節點
b9636a6ad0
當前提交
277dafbfb7
共有 3 個檔案被更改，包括 307 行新增 和 0 行删除
94
tp1.py
一般檔案
94
tp1.py
一般檔案
|
|
@ -0,0 +1,94 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import matplotlib.pyplot as plt
|
||||
from sklearn.neighbors import KNeighborsClassifier
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.model_selection import KFold
|
||||
import random
|
||||
import time
|
||||
|
||||
|
||||
"""
|
||||
from sklearn.datasets import fetch_openml
|
||||
mnist = fetch_openml('mnist_784')
|
||||
"""
|
||||
|
||||
"""
|
||||
---Ex 1---
|
||||
images = mnist.data.values.reshape((-1, 28, 28))
|
||||
plt.imshow(images[0],cmap=plt.cm.gray_r,interpolation="nearest")
|
||||
plt.show()
|
||||
|
||||
print(mnist.target[0])
|
||||
"""
|
||||
|
||||
"""
|
||||
---Ex 2---
|
||||
"""
|
||||
indices = [i for i in range(len(mnist.data))]
|
||||
random.shuffle(indices)
|
||||
indices = indices[:5000]
|
||||
|
||||
data = [mnist.data.values[i] for i in indices]
|
||||
target = [mnist.target[i] for i in indices]
|
||||
|
||||
bestClf = None
|
||||
bestScore = 0
|
||||
bestK = 0
|
||||
scores = []
|
||||
|
||||
kvalues = [i for i in range(2,16)]
|
||||
train_sizes = [0.05*i for i in range(1,20)]
|
||||
pvalues = [i for i in range(1,11)]
|
||||
|
||||
k = 3
|
||||
t = 0.9
|
||||
|
||||
start = time.time()
|
||||
xtrain, xtest, ytrain, ytest = train_test_split(data, target, train_size=t)
|
||||
clf = KNeighborsClassifier(3, n_jobs = 1)
|
||||
clf.fit(xtrain, ytrain)
|
||||
score = clf.score(xtest, ytest)
|
||||
end = time.time()
|
||||
print(f"n_jobs = 1, training + evaluating time : {end - start}")
|
||||
|
||||
start = time.time()
|
||||
xtrain, xtest, ytrain, ytest = train_test_split(data, target, train_size=t)
|
||||
clf = KNeighborsClassifier(3, n_jobs = -1)
|
||||
clf.fit(xtrain, ytrain)
|
||||
score = clf.score(xtest, ytest)
|
||||
end = time.time()
|
||||
print(f"n_jobs = -1, training + evaluating time : {end - start}")
|
||||
|
||||
|
||||
"""
|
||||
#for k in kvalues:
|
||||
#for t in train_sizes:
|
||||
for p in pvalues:
|
||||
print(p)
|
||||
xtrain, xtest, ytrain, ytest = train_test_split(data, target, train_size=t)
|
||||
clf = KNeighborsClassifier(k, p = p)
|
||||
clf.fit(xtrain, ytrain)
|
||||
score = clf.score(xtest, ytest)
|
||||
scores += [score]
|
||||
if score > bestScore:
|
||||
bestClf = clf
|
||||
#bestK = k
|
||||
#bestSize = t
|
||||
bestP = p
|
||||
bestScore = score
|
||||
|
||||
|
||||
print(target[4])
|
||||
print(bestClf.predict(data[4].reshape(1,-1)))
|
||||
plt.imshow(data[4].reshape(28, 28), cmap=plt.cm.gray_r, interpolation="nearest")
|
||||
plt.show()
|
||||
|
||||
#plt.plot(kvalues, scores)
|
||||
#plt.plot(train_sizes, scores)
|
||||
plt.plot(pvalues, scores)
|
||||
|
||||
print(bestScore)
|
||||
#print(bestSize)
|
||||
"""
|
||||
119
tp2.py
一般檔案
119
tp2.py
一般檔案
|
|
@ -0,0 +1,119 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import matplotlib.pyplot as plt
|
||||
from sklearn.neural_network import MLPClassifier
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.model_selection import KFold
|
||||
from sklearn.metrics import precision_score
|
||||
import random
|
||||
import time
|
||||
|
||||
"""
|
||||
from sklearn.datasets import fetch_openml
|
||||
mnist = fetch_openml('mnist_784')
|
||||
"""
|
||||
|
||||
"""
|
||||
|
||||
images = mnist.data.values.reshape((-1, 28, 28))
|
||||
plt.imshow(images[0],cmap=plt.cm.gray_r,interpolation="nearest")
|
||||
plt.show()
|
||||
|
||||
print(mnist.target[0])
|
||||
"""
|
||||
|
||||
|
||||
indices = [i for i in range(len(mnist.data))]
|
||||
random.shuffle(indices)
|
||||
indices = indices[:15000]
|
||||
|
||||
data = [mnist.data.values[i] for i in indices]
|
||||
target = [mnist.target[i] for i in indices]
|
||||
|
||||
bestClf = None
|
||||
bestScore = 0
|
||||
scores = []
|
||||
|
||||
train_sizes = [0.05*i for i in range(1,20)]
|
||||
|
||||
|
||||
xtrain, xtest, ytrain, ytest = train_test_split(data, target, train_size=0.7)
|
||||
|
||||
"""
|
||||
network = MLPClassifier(hidden_layer_sizes = (50))
|
||||
network.fit(xtrain, ytrain)
|
||||
ytest_pred = clf.predict(xtest)
|
||||
print("Average = macro:")
|
||||
print(precision_score(ytest, ytest_pred, average = "macro"))
|
||||
print("Average = None:")
|
||||
print(precision_score(ytest, ytest_pred, average = None))
|
||||
|
||||
print(target[4])
|
||||
print(network.predict(data[4].reshape(1,-1)))
|
||||
plt.imshow(data[4].reshape(28, 28), cmap=plt.cm.gray_r, interpolation="nearest")
|
||||
plt.show()
|
||||
"""
|
||||
|
||||
"""
|
||||
n_layers = [i for i in range(1,51)]
|
||||
|
||||
|
||||
for n in n_layers:
|
||||
print(n)
|
||||
network = MLPClassifier(hidden_layer_sizes = (50,)*n)
|
||||
network.fit(xtrain, ytrain)
|
||||
scores += [network.score(xtest, ytest)]
|
||||
|
||||
plt.plot(n_layers, scores)
|
||||
"""
|
||||
|
||||
"""
|
||||
for _ in range(5):
|
||||
n_layers = random.randint(1,3)
|
||||
layer_size = tuple([random.randint(10,300) for _ in range(n_layers)])
|
||||
print(layer_size)
|
||||
|
||||
network = MLPClassifier(hidden_layer_sizes = layer_size, solver = "adam", activation = "relu")
|
||||
network.fit(xtrain, ytrain)
|
||||
print(f"training time = {time.time() - start_time}, score = {network.score(xtest, ytest)}")
|
||||
"""
|
||||
|
||||
"""
|
||||
solvers = ["lbfgs", "sgd", "adam"]
|
||||
for s in solvers:
|
||||
print(s + ":")
|
||||
start_time = time.time()
|
||||
network = MLPClassifier(hidden_layer_sizes = (50,)*5, solver = s)
|
||||
network.fit(xtrain, ytrain)
|
||||
print(f"training time = {time.time() - start_time}, score = {network.score(xtest, ytest)}")
|
||||
"""
|
||||
|
||||
"""
|
||||
functions = ["identity", "logistic", "tanh", "relu"]
|
||||
|
||||
for f in functions:
|
||||
print(f + ":")
|
||||
start_time = time.time()
|
||||
network = MLPClassifier(hidden_layer_sizes = (50,)*5, activation = f)
|
||||
network.fit(xtrain, ytrain)
|
||||
print(f"training time = {time.time() - start_time}, score = {network.score(xtest, ytest)}")
|
||||
"""
|
||||
|
||||
times = []
|
||||
scores = []
|
||||
|
||||
for i in range(-7,7):
|
||||
alpha = 10**i
|
||||
print(f"alpha = {alpha}:")
|
||||
start_time = time.time()
|
||||
network = MLPClassifier(hidden_layer_sizes = (50,)*5, alpha = alpha)
|
||||
network.fit(xtrain, ytrain)
|
||||
trainingTime = time.time() - start_time
|
||||
score = network.score(xtest, ytest)
|
||||
times +=[trainingTime]
|
||||
scores += [score]
|
||||
|
||||
plt.plot([i for i in range(-7,7)], times)
|
||||
plt.show()
|
||||
plt.plot([i for i in range(-7,7)], scores)
|
||||
94
tp3.py
一般檔案
94
tp3.py
一般檔案
|
|
@ -0,0 +1,94 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import matplotlib.pyplot as plt
|
||||
from sklearn.neural_network import MLPClassifier
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.model_selection import KFold
|
||||
from sklearn.metrics import precision_score
|
||||
import random
|
||||
import time
|
||||
|
||||
"""
|
||||
from sklearn.datasets import fetch_openml
|
||||
mnist = fetch_openml('mnist_784')
|
||||
"""
|
||||
|
||||
"""
|
||||
---Ex 1---
|
||||
images = mnist.data.values.reshape((-1, 28, 28))
|
||||
plt.imshow(images[0],cmap=plt.cm.gray_r,interpolation="nearest")
|
||||
plt.show()
|
||||
|
||||
print(mnist.target[0])
|
||||
"""
|
||||
|
||||
"""
|
||||
---Ex 2---
|
||||
"""
|
||||
indices = [i for i in range(len(mnist.data))]
|
||||
random.shuffle(indices)
|
||||
indices = indices[:15000]
|
||||
|
||||
data = [mnist.data.values[i] for i in indices]
|
||||
target = [mnist.target[i] for i in indices]
|
||||
|
||||
bestClf = None
|
||||
bestScore = 0
|
||||
scores = []
|
||||
|
||||
train_sizes = [0.05*i for i in range(1,20)]
|
||||
|
||||
|
||||
xtrain, xtest, ytrain, ytest = train_test_split(data, target, train_size=0.7)
|
||||
"""
|
||||
network = MLPClassifier(hidden_layer_sizes = (50))
|
||||
network.fit(xtrain, ytrain)
|
||||
ytest_pred = clf.predict(xtest)
|
||||
print("Average = macro:")
|
||||
print(precision_score(ytest, ytest_pred, average = "macro"))
|
||||
print("Average = None:")
|
||||
print(precision_score(ytest, ytest_pred, average = None))
|
||||
|
||||
print(target[4])
|
||||
print(network.predict(data[4].reshape(1,-1)))
|
||||
plt.imshow(data[4].reshape(28, 28), cmap=plt.cm.gray_r, interpolation="nearest")
|
||||
plt.show()
|
||||
"""
|
||||
|
||||
"""
|
||||
n_layers = [i for i in range(1,51)]
|
||||
|
||||
|
||||
for n in n_layers:
|
||||
print(n)
|
||||
network = MLPClassifier(hidden_layer_sizes = (50,)*n)
|
||||
network.fit(xtrain, ytrain)
|
||||
scores += [network.score(xtest, ytest)]
|
||||
|
||||
plt.plot(n_layers, scores)
|
||||
"""
|
||||
|
||||
"""
|
||||
for _ in range(5):
|
||||
n_layers = random.randint(1,3)
|
||||
layer_size = tuple([random.randint(10,300) for _ in range(n_layers)])
|
||||
print(layer_size)
|
||||
|
||||
network = MLPClassifier(hidden_layer_sizes = layer_size, solver = "adam", activation = "relu")
|
||||
network.fit(xtrain, ytrain)
|
||||
print(f"training time = {time.time() - start_time}, score = {network.score(xtest, ytest)}")
|
||||
"""
|
||||
|
||||
"""
|
||||
solvers = ["lbfgs", "sgd", "adam"]
|
||||
for s in solvers:
|
||||
print(s + ":")
|
||||
start_time = time.time()
|
||||
network = MLPClassifier(hidden_layer_sizes = (50,)*5, solver = s)
|
||||
network.fit(xtrain, ytrain)
|
||||
print(f"training time = {time.time() - start_time}, score = {network.score(xtest, ytest)}")
|
||||
"""
|
||||
載入中…
新增問題並參考