Introduction to Essential Python Data Science Libraries with Example Code

NumPy : A fundamental library for handling large multi‑dimensional arrays and matrices.

import numpy as np
# 创建一个2x2的数组
arr = np.array([[1, 2], [3, 4]])
print(arr)
# 计算数组的平均值
mean = np.mean(arr)
print(mean)

Pandas : Provides the DataFrame data structure for flexible data analysis.

import pandas as pd
# 创建一个简单的DataFrame
data = {'Name': ['Tom', 'Nick', 'John'], 'Age': [20, 21, 19]}
df = pd.DataFrame(data)
print(df)
# 对Age列进行排序
sorted_df = df.sort_values('Age')
print(sorted_df)

Matplotlib : A plotting library for creating static, animated, and interactive visualizations.

import matplotlib.pyplot as plt
# 创建一些数据点
x = [1, 2, 3, 4]
y = [10, 20, 30, 40]
# 绘制线图
plt.plot(x, y)
plt.xlabel('X-axis')
plt.ylabel('Y-axis')
plt.title('Simple Line Plot')
plt.show()

Seaborn : Built on Matplotlib, it offers higher‑level statistical graphics.

import seaborn as sns
import pandas as pd
# 加载内置数据集
tips = sns.load_dataset("tips")
# 绘制箱线图
sns.boxplot(x="day", y="total_bill", data=tips)
plt.show()

SciPy : Supplies a collection of scientific computing tools.

from scipy import stats
# 创建一些随机数据
data = np.random.randn(100)
# 计算数据的正态性检验
normality_test_result = stats.shapiro(data)
print(normality_test_result)

Statsmodels : Used for estimating and testing statistical models.

import statsmodels.api as sm
import pandas as pd
# 加载内置数据集
data = sm.datasets.get_rdataset('mtcars').data
# 构建线性回归模型
X = data[['wt']]
y = data['mpg']
model = sm.OLS(y, X).fit()
print(model.summary())

Scikit-learn : A versatile library for machine learning and data mining.

from sklearn.linear_model import LinearRegression
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
# 加载波士顿房价数据集
boston = load_boston()
X = boston.data
y = boston.target
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# 训练线性回归模型
model = LinearRegression()
model.fit(X_train, y_train)
# 预测测试集结果
predictions = model.predict(X_test)

BeautifulSoup : A library for web scraping and parsing HTML documents.

from bs4 import BeautifulSoup
import requests
# 获取网页内容
url = "https://www.example.com"
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
# 提取所有标题元素
headings = soup.find_all(['h1', 'h2', 'h3'])
for heading in headings:
    print(heading.text)

TensorFlow : An open‑source platform for deep learning and neural networks.

import tensorflow as tf
import numpy as np
# 创建一个简单的线性模型
model = tf.keras.models.Sequential([
    tf.keras.layers.Dense(units=1, input_shape=[1])
])
# 编译模型
model.compile(optimizer='sgd', loss='mean_squared_error')
# 准备训练数据
x_train = np.array([1, 2, 3, 4]).reshape(-1, 1)
y_train = np.array([2, 4, 6, 8])
# 训练模型
model.fit(x_train, y_train, epochs=500)
# 预测新数据
x_test = np.array([5]).reshape(-1, 1)
prediction = model.predict(x_test)
print(prediction)

Plotly : A library for creating interactive data visualizations.

import plotly.express as px
import pandas as pd
# 加载内置数据集
df = px.data.iris()
# 创建交互式散点图
fig = px.scatter(df, x="sepal_width", y="sepal_length", color="species")
fig.show()