def calculate_pe_ratio(market_cap, net_profit):
    pe_ratio = market_cap / net_profit
    return pe_ratio

# 示例用法
market_cap = 1000000000  # 市值为10亿美元
net_profit = 50000000  # 净利润为5000万美元
pe_ratio = calculate_pe_ratio(market_cap, net_profit)
print("市盈率为:", pe_ratio)

pip install pandas
pip install numpy
pip install scipy
pip install seaborn
pip install matplotlib

# 机器学习部分
pip install scikit-learn

import numpy as np

data = [1, 2, 3, 4, 5]
mean = np.mean(data)
print(mean)

import numpy as np

data = [1, 2, 3, 4, 5]
median = np.median(data)
print(median)

import scipy.stats as stats

data = [1, 2, 2, 3, 4, 4, 4, 5]
mode = stats.mode(data)
print(mode)

import numpy as np

data = [1, 2, 3, 4, 5]
variance = np.var(data)
print(variance)

import numpy as np

data = [1, 2, 3, 4, 5]
std_dev = np.std(data)
print(std_dev)

import matplotlib.pyplot as plt

x = [1, 2, 3, 4, 5]
y = [2, 4, 6, 8, 10]

plt.plot(x, y)
plt.show()

import matplotlib.pyplot as plt

x = [1, 2, 3, 4, 5]
y = [2, 4, 6, 8, 10]

plt.scatter(x, y)
plt.show()

import matplotlib.pyplot as plt

data = [1, 2, 2, 3, 4, 4, 4, 5]

plt.hist(data, bins=5)
plt.show()

import seaborn as sns

data = [1, 2, 2, 3, 4, 4, 4, 5]

sns.boxplot(data)
plt.show()

import matplotlib.pyplot as plt

categories = ['A', 'B', 'C', 'D']
values = [10, 20, 30, 40]

plt.bar(categories, values)
plt.show()

import pandas as pd

# 创建数据集
data = {'sales_date': ['2022-01-01', '2022-01-02', '2022-01-03', '2022-01-04', '2022-01-05', '2022-01-06', '2022-01-07', '2022-01-08', '2022-01-09', '2022-01-10'],
        'sales_amount': [100, 200, 150, 300, 250, 400, 350, 450, 500, 600],
        'sales_person': ['John', 'Jane', 'John', 'Jane', 'John', 'Jane', 'John', 'Jane', 'John', 'Jane']}

df = pd.DataFrame(data)

# 按销售员名称分组，并对每个组的销售金额求和
grouped = df.groupby('sales_person')['sales_amount'].sum()

print(grouped)

sales_person
Jane    2200
John    1800
Name: sales_amount, dtype: int64

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 创建数据集
data = {'age': [22, 25, 47, 52, 21, 62, 41, 36, 28, 44],
        'income': [21000, 22000, 52000, 73000, 18000, 87000, 45000, 33000, 28000, 84000],
        'gender': ['M', 'F', 'F', 'M', 'M', 'M', 'F', 'M', 'F', 'M'],
        'bought': ['N', 'N', 'Y', 'Y', 'N', 'Y', 'Y', 'N', 'Y', 'Y']}

df = pd.DataFrame(data)

# 将文本数据转换成数值数据
df['gender'] = df['gender'].map({'M': 0, 'F': 1})
df['bought'] = df['bought'].map({'N': 0, 'Y': 1})

# 将数据集分成训练集和测试集
X = df[['age', 'income', 'gender']]
y = df['bought']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

# 创建决策树模型
model = DecisionTreeClassifier()

# 训练模型
model.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = model.predict(X_test)

# 计算模型的准确率
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy: {:.2f}%".format(accuracy*100))

Accuracy: 50.00%

pip install rows

state,city,inhabitants,area
AC,Acrelândia,12538,1807.92
AC,Assis Brasil,6072,4974.18
AC,Brasiléia,21398,3916.5
AC,Bujari,8471,3034.87
AC,Capixaba,8798,1702.58
[...]
RJ,Angra dos Reis,169511,825.09
RJ,Aperibé,10213,94.64
RJ,Araruama,112008,638.02
RJ,Areal,11423,110.92
RJ,Armação dos Búzios,27560,70.28
[...]

import rows

cities = rows.import_from_csv("data/brazilian-cities.csv")
rio_biggest_cities = [
    city for city in cities
    if city.state == "RJ" and city.inhabitants > 500000
]
for city in rio_biggest_cities:
    density = city.inhabitants / city.area
    print(f"{city.city} ({density:5.2f} ppl/km²)")

from collections import OrderedDict
from rows import fields, Table


country_fields = OrderedDict([
    ("name", fields.TextField),
    ("population", fields.IntegerField),
])

countries = Table(fields=country_fields)
countries.append({"name": "Argentina", "population": "45101781"})
countries.append({"name": "Brazil", "population": "212392717"})
countries.append({"name": "Colombia", "population": "49849818"})
countries.append({"name": "Ecuador", "population": "17100444"})
countries.append({"name": "Peru", "population": "32933835"})

for country in countries:
    print(country)
# Result:
#     Row(name='Argentina', population=45101781)
#     Row(name='Brazil', population=212392717)
#     Row(name='Colombia', population=49849818)
#     Row(name='Ecuador', population=17100444)
#     Row(name='Peru', population=32933835)
# "Row" is a namedtuple created from `country_fields`

# We've added population as a string, the library automatically converted to
# integer so we can also sum:
countries_population = sum(country.population for country in countries)
print(countries_population)  # prints 357378595

# 公众号：Python实用宝典
import rows
rows.export_to_csv(countries, "some-LA-countries.csv")

# html
rows.export_to_html(legislators, "some-LA-countries.csv")

import rows

data = [
    {"name": "Argentina", "population": "45101781"},
    {"name": "Brazil", "population": "212392717"},
    {"name": "Colombia", "population": "49849818"},
    {"name": "Ecuador", "population": "17100444"},
    {"name": "Peru", "population": "32933835"},
    {"name": "Guyana", },  # Missing "population", will fill with `None`
]
table = rows.import_from_dicts(data)
print(table[-1])  # Can use indexes
# Result:
#     Row(name='Guyana', population=None)

# 需要提前安装: pip install rows[pdf]
URL="http://www.imprensaoficial.rr.gov.br/app/_edicoes/2018/01/doe-20180131.pdf"
rows pdf-to-text $URL result.txt  # 保存到文件 显示进度条
rows pdf-to-text --quiet $URL result.txt  # 保存到文件 不显示进度条
rows pdf-to-text --pages=1,2,3 $URL # 输出三页到终端
rows pdf-to-text --pages=1-3 $URL # 输出三页到终端(使用 - 范围符)

rows csv2sqlite \
     --dialect=excel \
     --input-encoding=latin1 \
     file1.csv file2.csv \
     result.sqlite

rows csv-merge \
     file1.csv file2.csv.bz2 file3.csv.xz \
     result.csv.gz

# needs: pip install rows[html]
rows query \
    "SELECT * FROM table1 WHERE inhabitants > 1000000" \
    data/brazilian-cities.csv \
    --output=data/result.html