数据分析必会的十个 Python 库

pip install scikit-learn
1.

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

df = pd.read_csv('data.csv')
X = df.drop('target', axis=1)
y = df['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
model = LogisticRegression().fit(X_train, y_train)
y_pred = model.predict(X_test)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.

pip install statsmodels
1.

import statsmodels.api as sm
import pandas as pd

df = pd.read_csv('data.csv')
model = sm.OLS(endog=df['target'], exog=df[['X1', 'X2']])
results = model.fit()
print(results.summary())
1.
2.
3.
4.
5.
6.
7.

pip install scipy
1.

import numpy as np
from scipy.optimize import minimize

def objective(x):
    return np.sum((x[0] - x[1])**2)

start = np.array([1, 1])
opt = minimize(objective, start, method='TNC')
print(opt.x)
1.
2.
3.
4.
5.
6.
7.
8.
9.

import tensorflow as tf

model = tf.keras.Sequential([
     tf.keras.layers.Dense(64, input_shape=(1000,)),
     tf.keras.layers.Dense(1),
     tf.keras.layers.Activation('sigmoid')
 ])
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=100, validation_split=0.2)
1.
2.
3.
4.
5.
6.
7.
8.
9.

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

model = Sequential()
model.add(Dense(64, input_shape=(1000,)))
model.add(Dense(1))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=100, validation_split=0.2)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.

import torch
import torch.nn as nn
import torch.optim as optim

# 创建一个简单的线性模型
model = nn.Linear(in_features=1, out_features=1)

# 定义损失函数和优化器
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)

# 示例数据
x_train = torch.tensor([[1.0], [2.0], [3.0]])
y_train = torch.tensor([[2.0], [4.0], [6.0]])

# 训练模型
for epoch in range(1000):
    model.train()
    optimizer.zero_grad()
    
    # 正向传播
    y_pred = model(x_train)
    
    # 计算损失
    loss = criterion(y_pred, y_train)
    
    # 反向传播和优化
    loss.backward()
    optimizer.step()

# 测试模型
model.eval()
with torch.no_grad():
    y_pred = model(torch.tensor([[4.0]]))
    print(y_pred)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.

import pyspark.sql.functions as F

df = spark.createDataFrame([(1, 'A'), (2, 'B'), (3, 'C'), (4, 'B')], ['id', 'word'])
result = df.groupBy('word').count().orderBy('count', ascending=False)
result.show()
1.
2.
3.
4.
5.

pip install requests
1.

import requests
response = requests.get('https://example.com')
print(response.status_code)
1.
2.
3.

pip install beautifulsoup4
1.

from bs4 import BeautifulSoup

html = '<ul><li>1</li><li>2</li><li>3</li></ul>'
soup = BeautifulSoup(html, 'html.parser')
li_list = soup.find_all('li')
for li in li_list:
    print(li.get_text())
1.
2.
3.
4.
5.
6.
7.

from flask import Flask

app = Flask(__name__)
@app.route('/')
def hello():
     return 'Hello, World!'
app.run()
1.
2.
3.
4.
5.
6.
7.