盘点20个Python数据科学库神器打造数据魔法世界

import numpy as np

# 创建一个数组
array = np.array([1, 2, 3, 4, 5])

# 数组运算
result = array * 2
print(result)

import pandas as pd

# 创建一个 DataFrame
data = {'Name': ['Alice', 'Bob', 'Charlie'],
        'Age': [25, 30, 35]}
df = pd.DataFrame(data)

# 显示数据框架
print(df)

import matplotlib.pyplot as plt

# 绘制折线图
x = np.linspace(0, 10, 100)
y = np.sin(x)
plt.plot(x, y)
plt.show()

import seaborn as sns

# 绘制热图
data = np.random.rand(10, 12)
sns.heatmap(data)
plt.show()

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC

# 加载鸢尾花数据集
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2)

# 训练支持向量机模型
model = SVC()
model.fit(X_train, y_train)

import tensorflow as tf

# 创建神经网络模型
model = tf.keras.Sequential([
    tf.keras.layers.Dense(10, activation='relu', input_shape=(4,)),
    tf.keras.layers.Dense(3, activation='softmax')
])

from keras.models import Sequential
from keras.layers import Dense

# 创建神经网络模型
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

import statsmodels.api as sm

# 拟合线性回归模型
X = np.random.rand(100, 2)
y = X.dot(np.array([1, 2])) + np.random.normal(0, 0.1, 100)
model = sm.OLS(y, X).fit()
print(model.summary())

from scipy.optimize import minimize

# 定义优化函数
def rosen(x):
    return sum(100.0 * (x[1:] - x[:-1]**2)**2 + (1 - x[:-1])**2)

# 最小化函数
x0 = np.array([1.3, 0.7, 0.8, 1.9, 1.2])
res = minimize(rosen, x0, method='nelder-mead', options={'xatol': 1e-8, 'disp': True})
print(res.x)

import plotly.express as px

# 绘制散点图
df = px.data.iris()
fig = px.scatter(df, x="sepal_width", y="sepal_length", color="species")
fig.show()

import networkx as nx

# 创建一个图
G = nx.Graph()
G.add_node(1)
G.add_nodes_from([2, 3])
G.add_edge(1, 2)

import nltk
from nltk.tokenize import word_tokenize

text = "Hello, how are you?"
tokens = word_tokenize(text)
print(tokens)

from bs4 import BeautifulSoup
import requests

# 从网页抓取信息
url = "https://en.wikipedia.org/wiki/Data_science"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
print(soup.title)

from gensim.summarization import keywords
from gensim import corpora

# 提取关键字
text = "Natural language processing (NLP) is a field " \
       "focused on making sense of and working with text data."
kw = keywords(text)
print(kw)

import torch

# 创建张量
x = torch.rand(5, 3)
print(x)

import dask.dataframe as dd

# 创建大型数据框架
df = dd.read_csv('large_dataset.csv')
result = df.groupby('column').value.mean().compute()
print(result)

from bokeh.plotting import figure, output_file, show

# 绘制直方图
output_file("histogram.html")
p = figure()
p.vbar(x=[1, 2, 3], width=0.5, bottom=0, top=[1, 2, 3])
show(p)

import tensorflow_probability as tfp

# 定义正态分布
normal = tfp.distributions.Normal(loc=0., scale=1.)
samples = normal.sample(100)
print(samples)

from yellowbrick.datasets import load_concrete
from yellowbrick.regressor import ResidualsPlot
from sklearn.linear_model import Ridge

# 加载数据集
X, y = load_concrete()

# 可视化回归残差
model = Ridge()
visualizer = ResidualsPlot(model)
visualizer.fit(X, y)
visualizer.show()

import xgboost as xgb

# 加载数据
data = np.random.rand(5, 10)
labels = np.random.randint(2, size=5)

# 构建 DMatrix
dtrain = xgb.DMatrix(data, label=labels)