Python 机器学习最常打交道的 27 款工具包

import numpy as np
import math
import random
import time
start = time.time()
for i in range(10):
   list_1 = list(range(1,10000))
   for j in range(len(list_1)):
       list_1[j] = math.sin(list_1[j])
print("使用纯Python用时{}s".format(time.time()-start))
start = time.time()
for i in range(10):
   list_1 = np.array(np.arange(1,10000))
   list_1 = np.sin(list_1)
print("使用Numpy用时{}s".format(time.time()-start))

使用纯Python用时0.017444372177124023s
使用Numpy用时0.001619577407836914s

import numpy as np
import cv2 as cv
from matplotlib import pyplot as plt
img = cv.imread('h89817032p0.png')
kernel = np.ones((5,5),np.float32)/25
dst = cv.filter2D(img,-1,kernel)
blur_1 = cv.GaussianBlur(img,(5,5),0)
blur_2 = cv.bilateralFilter(img,9,75,75)
plt.figure(figsize=(10,10))
plt.subplot(221),plt.imshow(img[:,:,::-1]),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(222),plt.imshow(dst[:,:,::-1]),plt.title('Averaging')
plt.xticks([]), plt.yticks([])
plt.subplot(223),plt.imshow(blur_1[:,:,::-1]),plt.title('Gaussian')
plt.xticks([]), plt.yticks([])
plt.subplot(224),plt.imshow(blur_1[:,:,::-1]),plt.title('Bilateral')
plt.xticks([]), plt.yticks([])
plt.show()

from skimage import data, color, io
from skimage.transform import rescale, resize, downscale_local_mean
image = color.rgb2gray(io.imread('h89817032p0.png'))
image_rescaled = rescale(image, 0.25, anti_aliasing=False)
image_resized = resize(image, (image.shape[0] // 4, image.shape[1] // 4),
                      anti_aliasing=True)
image_downscaled = downscale_local_mean(image, (4, 3))
plt.figure(figsize=(20,20))
plt.subplot(221),plt.imshow(image, cmap='gray'),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(222),plt.imshow(image_rescaled, cmap='gray'),plt.title('Rescaled')
plt.xticks([]), plt.yticks([])
plt.subplot(223),plt.imshow(image_resized, cmap='gray'),plt.title('Resized')
plt.xticks([]), plt.yticks([])
plt.subplot(224),plt.imshow(image_downscaled, cmap='gray'),plt.title('Downscaled')
plt.xticks([]), plt.yticks([])
plt.show()

from PIL import Image, ImageDraw, ImageFont, ImageFilter
import random
# 随机字母:
def rndChar():
   return chr(random.randint(65, 90))
# 随机颜色1:
def rndColor():
   return (random.randint(64, 255), random.randint(64, 255), random.randint(64, 255))
# 随机颜色2:
def rndColor2():
   return (random.randint(32, 127), random.randint(32, 127), random.randint(32, 127))
# 240 x 60:
width = 60 * 6
height = 60 * 6
image = Image.new('RGB', (width, height), (255, 255, 255))
# 创建Font对象:
font = ImageFont.truetype('/usr/share/fonts/wps-office/simhei.ttf', 60)
# 创建Draw对象:
draw = ImageDraw.Draw(image)
# 填充每个像素:
for x in range(width):
   for y in range(height):
       draw.point((x, y), fill=rndColor())
# 输出文字:
for t in range(6):
   draw.text((60 * t + 10, 150), rndChar(), font=font, fill=rndColor2())
# 模糊:
image = image.filter(ImageFilter.BLUR)
image.save('code.jpg', 'jpeg')

from SimpleCV import Image, Color, Display
# load an image from imgur
img = Image('http://i.imgur.com/lfAeZ4n.png')
# use a keypoint detector to find areas of interest
feats = img.findKeypoints()
# draw the list of keypoints
feats.draw(color=Color.RED)
# show the  resulting image.  
img.show()
# apply the stuff we found to the image.
output = img.applyLayers()
# save the results.
output.save('juniperfeats.png')

SyntaxError: Missing parentheses in call to 'print'. Did you mean print('unit test')?

import numpy as np
import mahotas
import mahotas.demos
from mahotas.thresholding import soft_threshold
from matplotlib import pyplot as plt
from os import path
f = mahotas.demos.load('lena', as_grey=True)
f = f[128:,128:]
plt.gray()
# Show the data:
print("Fraction of zeros in original image: {0}".format(np.mean(f==0)))
plt.imshow(f)
plt.show()

import time
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import MiniBatchKMeans, KMeans
from sklearn.metrics.pairwise import pairwise_distances_argmin
from sklearn.datasets import make_blobs
# Generate sample data
np.random.seed(0)
batch_size = 45
centers = [[1, 1], [-1, -1], [1, -1]]
n_clusters = len(centers)
X, labels_true = make_blobs(n_samples=3000, centers=centers, cluster_std=0.7)
# Compute clustering with Means
k_means = KMeans(init='k-means++', n_clusters=3, n_init=10)
t0 = time.time()
k_means.fit(X)
t_batch = time.time() - t0
# Compute clustering with MiniBatchKMeans
mbk = MiniBatchKMeans(init='k-means++', n_clusters=3, batch_size=batch_size,
                     n_init=10, max_no_improvement=10, verbose=0)
t0 = time.time()
mbk.fit(X)
t_mini_batch = time.time() - t0
# Plot result
fig = plt.figure(figsize=(8, 3))
fig.subplots_adjust(left=0.02, right=0.98, bottom=0.05, top=0.9)
colors = ['#4EACC5', '#FF9C34', '#4E9A06']
# We want to have the same colors for the same cluster from the
# MiniBatchKMeans and the KMeans algorithm. Let's pair the cluster centers per
# closest one.
k_means_cluster_centers = k_means.cluster_centers_
order = pairwise_distances_argmin(k_means.cluster_centers_,
                                 mbk.cluster_centers_)
mbk_means_cluster_centers = mbk.cluster_centers_[order]
k_means_labels = pairwise_distances_argmin(X, k_means_cluster_centers)
mbk_means_labels = pairwise_distances_argmin(X, mbk_means_cluster_centers)
# KMeans
for k, col in zip(range(n_clusters), colors):
   my_members = k_means_labels == k
   cluster_center = k_means_cluster_centers[k]
   plt.plot(X[my_members, 0], X[my_members, 1], 'w',
           markerfacecolor=col, marker='.')
   plt.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col,
           markeredgecolor='k', markersize=6)
plt.title('KMeans')
plt.xticks(())
plt.yticks(())
plt.show()

from scipy import special
import matplotlib.pyplot as plt
import numpy as np
def drumhead_height(n, k, distance, angle, t):
   kth_zero = special.jn_zeros(n, k)[-1]
   return np.cos(t) * np.cos(n*angle) * special.jn(n, distance*kth_zero)
theta = np.r_[0:2*np.pi:50j]
radius = np.r_[0:1:50j]
x = np.array([r * np.cos(theta) for r in radius])
y = np.array([r * np.sin(theta) for r in radius])
z = np.array([drumhead_height(1, 1, r, theta, 0.5) for r in radius])
fig = plt.figure()
ax = fig.add_axes(rect=(0, 0.05, 0.95, 0.95), projection='3d')
ax.plot_surface(x, y, z, rstride=1, cstride=1, cmap='RdBu_r', vmin=-0.5, vmax=0.5)
ax.set_xlabel('X')
ax.set_ylabel('Y')
ax.set_xticks(np.arange(-1, 1.1, 0.5))
ax.set_yticks(np.arange(-1, 1.1, 0.5))
ax.set_zlabel('Z')
plt.show()

import nltk
from nltk.corpus import treebank
# 首次使用需要下载
nltk.download('punkt')
nltk.download('averaged_perceptron_tagger')
nltk.download('maxent_ne_chunker')
nltk.download('words')
nltk.download('treebank')
sentence = """At eight o'clock on Thursday morning Arthur didn't feel very good."""
# Tokenize
tokens = nltk.word_tokenize(sentence)
tagged = nltk.pos_tag(tokens)
# Identify named entities
entities = nltk.chunk.ne_chunk(tagged)
# Display a parse tree
t = treebank.parsed_sents('wsj_0001.mrg')[0]
t.draw()

import spacy
 texts = [
     "Net income was $9.4 million compared to the prior year of $2.7 million.",
     "Revenue exceeded twelve billion dollars, with a loss of $1b.",
 ]
 nlp = spacy.load("en_core_web_sm")
 for doc in nlp.pipe(texts, disable=["tok2vec", "tagger", "parser", "attribute_ruler", "lemmatizer"]):
     # Do something with the doc here
     print([(ent.text, ent.label_) for ent in doc.ents])

[('$9.4 million', 'MONEY'), ('the prior year', 'DATE'), ('$2.7 million', 'MONEY')]
[('twelve billion dollars', 'MONEY'), ('1b', 'MONEY')]

# Beat tracking example
import librosa
# 1. Get the file path to an included audio example
filename = librosa.example('nutcracker')
# 2. Load the audio as a waveform `y`
#    Store the sampling rate as `sr`
y, sr = librosa.load(filename)
# 3. Run the default beat tracker
tempo, beat_frames = librosa.beat.beat_track(y=y, sr=sr)
print('Estimated tempo: {:.2f} beats per minute'.format(tempo))
# 4. Convert the frame indices of beat events into timestamps
beat_times = librosa.frames_to_time(beat_frames, sr=sr)

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
ts = pd.Series(np.random.randn(1000), index=pd.date_range("1/1/2000", periods=1000))
ts = ts.cumsum()
df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index, columns=list("ABCD"))
df = df.cumsum()
df.plot()
plt.show()

# plot_multi_curve.py
import numpy as np
import matplotlib.pyplot as plt
x = np.linspace(0.1, 2 * np.pi, 100)
y_1 = x
y_2 = np.square(x)
y_3 = np.log(x)
y_4 = np.sin(x)
plt.plot(x,y_1)
plt.plot(x,y_2)
plt.plot(x,y_3)
plt.plot(x,y_4)
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt
sns.set_theme(style="ticks")
df = sns.load_dataset("penguins")
sns.pairplot(df, hue="species")
plt.show()

$ pip install orange3

$ orange-canvas

from pybrain.structure import FeedForwardNetwork
n = FeedForwardNetwork()

from pybrain.structure import LinearLayer, SigmoidLayer
inLayer = LinearLayer(2)
hiddenLayer = SigmoidLayer(3)
outLayer = LinearLayer(1)

n.addInputModule(inLayer)
n.addModule(hiddenLayer)
n.addOutputModule(outLayer)

from pybrain.structure import FullConnection
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_out = FullConnection(hiddenLayer, outLayer)

n.addConnection(in_to_hidden)
n.addConnection(hidden_to_out)

n.sortModules()

import numpy as np
import milk
features = np.random.rand(100,10)
labels = np.zeros(100)
features[50:] += .5
labels[50:] = 1
learner = milk.defaultclassifier()
model = learner.train(features, labels)
# Now you can use the model on new examples:
example = np.random.rand(10)
print(model.apply(example))
example2 = np.random.rand(10)
example2 += .5
print(model.apply(example2))

import tensorflow as tf
from tensorflow.keras import datasets, layers, models
# 数据加载
(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()
# 数据预处理
train_images, test_images = train_images / 255.0, test_images / 255.0
# 模型构建
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10))
# 模型编译与训练
model.compile(optimizer='adam',
             loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
             metrics=['accuracy'])
history = model.fit(train_images, train_labels, epochs=10,  
                   validation_data=(test_images, test_labels))

# 导入库
import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda, Compose
import matplotlib.pyplot as plt
# 模型构建
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
# Define model
class NeuralNetwork(nn.Module):
   def __init__(self):
       super(NeuralNetwork, self).__init__()
       self.flatten = nn.Flatten()
       self.linear_relu_stack = nn.Sequential(
           nn.Linear(28*28, 512),
           nn.ReLU(),
           nn.Linear(512, 512),
           nn.ReLU(),
           nn.Linear(512, 10),
           nn.ReLU()
       )
   def forward(self, x):
       x = self.flatten(x)
       logits = self.linear_relu_stack(x)
       return logits
model = NeuralNetwork().to(device)
# 损失函数和优化器
loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)
# 模型训练
def train(dataloader, model, loss_fn, optimizer):
   size = len(dataloader.dataset)
   for batch, (X, y) in enumerate(dataloader):
       X, y = X.to(device), y.to(device)
       # Compute prediction error
       pred = model(X)
       loss = loss_fn(pred, y)
       # Backpropagation
       optimizer.zero_grad()
       loss.backward()
       optimizer.step()
       if batch % 100 == 0:
           loss, current = loss.item(), batch * len(X)
           print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")

import theano
import theano.tensor as T
x = T.dvector('x')
y = x ** 2
J, updates = theano.scan(lambda i, y,x : T.grad(y[i], x), sequences=T.arange(y.shape[0]), non_sequences=[y,x])
f = theano.function([x], J, updates=updates)
f([4, 4])

from keras.models import Sequential
from keras.layers import Dense
# 模型构建
model = Sequential()
model.add(Dense(units=64, activation='relu', input_dim=100))
model.add(Dense(units=10, activation='softmax'))
# 模型编译与训练
model.compile(loss='categorical_crossentropy',
             optimizer='sgd',
             metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5, batch_size=32)

import mxnet as mx
from mxnet import gluon
from mxnet.gluon import nn
from mxnet import autograd as ag
import mxnet.ndarray as F
# 数据加载
mnist = mx.test_utils.get_mnist()
batch_size = 100
train_data = mx.io.NDArrayIter(mnist['train_data'], mnist['train_label'], batch_size, shuffle=True)
val_data = mx.io.NDArrayIter(mnist['test_data'], mnist['test_label'], batch_size)
# CNN模型
class Net(gluon.Block):
   def __init__(self, **kwargs):
       super(Net, self).__init__(**kwargs)
       self.conv1 = nn.Conv2D(20, kernel_size=(5,5))
       self.pool1 = nn.MaxPool2D(pool_size=(2,2), strides = (2,2))
       self.conv2 = nn.Conv2D(50, kernel_size=(5,5))
       self.pool2 = nn.MaxPool2D(pool_size=(2,2), strides = (2,2))
       self.fc1 = nn.Dense(500)
       self.fc2 = nn.Dense(10)
   def forward(self, x):
       x = self.pool1(F.tanh(self.conv1(x)))
       x = self.pool2(F.tanh(self.conv2(x)))
       # 0 means copy over size from corresponding dimension.
       # -1 means infer size from the rest of dimensions.
       x = x.reshape((0, -1))
       x = F.tanh(self.fc1(x))
       x = F.tanh(self.fc2(x))
       return x
net = Net()
# 初始化与优化器定义
# set the context on GPU is available otherwise CPU
ctx = [mx.gpu() if mx.test_utils.list_gpus() else mx.cpu()]
net.initialize(mx.init.Xavier(magnitude=2.24), ctx=ctx)
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.03})
# 模型训练
# Use Accuracy as the evaluation metric.
metric = mx.metric.Accuracy()
softmax_cross_entropy_loss = gluon.loss.SoftmaxCrossEntropyLoss()
for i in range(epoch):
   # Reset the train data iterator.
   train_data.reset()
   for batch in train_data:
       data = gluon.utils.split_and_load(batch.data[0], ctx_list=ctx, batch_axis=0)
       label = gluon.utils.split_and_load(batch.label[0], ctx_list=ctx, batch_axis=0)
       outputs = []
       # Inside training scope
       with ag.record():
           for x, y in zip(data, label):
               z = net(x)
               # Computes softmax cross entropy loss.
               loss = softmax_cross_entropy_loss(z, y)
               # Backpropogate the error for one iteration.
               loss.backward()
               outputs.append(z)
       metric.update(label, outputs)
       trainer.step(batch.data[0].shape[0])
   # Gets the evaluation result.
   name, acc = metric.get()
   # Reset evaluation result to initial state.
   metric.reset()
   print('training acc at epoch %d: %s=%f'%(i, name, acc))

# 导入需要的包
import paddle
import numpy as np
from paddle.nn import Conv2D, MaxPool2D, Linear
## 组网
import paddle.nn.functional as F
# 定义 LeNet 网络结构
class LeNet(paddle.nn.Layer):
   def __init__(self, num_classes=1):
       super(LeNet, self).__init__()
       # 创建卷积和池化层
       # 创建第1个卷积层
       self.conv1 = Conv2D(in_channels=1, out_channels=6, kernel_size=5)
       self.max_pool1 = MaxPool2D(kernel_size=2, stride=2)
       # 尺寸的逻辑：池化层未改变通道数；当前通道数为6
       # 创建第2个卷积层
       self.conv2 = Conv2D(in_channels=6, out_channels=16, kernel_size=5)
       self.max_pool2 = MaxPool2D(kernel_size=2, stride=2)
       # 创建第3个卷积层
       self.conv3 = Conv2D(in_channels=16, out_channels=120, kernel_size=4)
       # 尺寸的逻辑：输入层将数据拉平[B,C,H,W] -> [B,C*H*W]
       # 输入size是[28,28]，经过三次卷积和两次池化之后，C*H*W等于120
       self.fc1 = Linear(in_features=120, out_features=64)
       # 创建全连接层，第一个全连接层的输出神经元个数为64， 第二个全连接层输出神经元个数为分类标签的类别数
       self.fc2 = Linear(in_features=64, out_features=num_classes)
   # 网络的前向计算过程
   def forward(self, x):
       x = self.conv1(x)
       # 每个卷积层使用Sigmoid激活函数，后面跟着一个2x2的池化
       x = F.sigmoid(x)
       x = self.max_pool1(x)
       x = F.sigmoid(x)
       x = self.conv2(x)
       x = self.max_pool2(x)
       x = self.conv3(x)
       # 尺寸的逻辑：输入层将数据拉平[B,C,H,W] -> [B,C*H*W]
       x = paddle.reshape(x, [x.shape[0], -1])
       x = self.fc1(x)
       x = F.sigmoid(x)
       x = self.fc2(x)
       return x

NDLNetworkBuilder=[
   run=ndlLR
   ndlLR=[
     # sample and label dimensions
     SDim=$dimension$
     LDim=1
     features=Input(SDim, 1)
     labels=Input(LDim, 1)
     # parameters to learn
      B0 = Parameter(4)  
     W0 = Parameter(4, SDim)
     B = Parameter(LDim)
     W = Parameter(LDim, 4)
     # operations
     t0 = Times(W0, features)
     z0 = Plus(t0, B0)
      s0 = Sigmoid(z0)    
     t = Times(W, s0)
     z = Plus(t, B)
     s = Sigmoid(z)    
     LR = Logistic(labels, s)
     EP = SquareError(labels, s)
     # root nodes
     FeatureNodes=(features)
     LabelNodes=(labels)
     CriteriaNodes=(LR)
     EvalNodes=(EP)
     OutputNodes=(s,t,z,s0,W0)
    ]    
 ]