使用rpy2，您可以在Python项目中直接调用R的强大功能，无需切换环境或学习新工具。

pip install rpy2

import rpy2
print(rpy2.__version__)

from rpy2 import robjects

# 执行简单R命令
robjects.r('''
    # 创建R向量
    vec <- c(1, 2, 3, 4, 5)
    # 计算平均值
    mean_val <- mean(vec)
    # 打印结果
    print(mean_val)
''')

# 获取R变量到Python环境
r_mean = robjects.globalenv['mean_val']
print(f"在Python中获取的R计算结果: {r_mean[0]}")

输出结果：

import numpy as np
import pandas as pd
from rpy2.robjects import pandas2ri
from rpy2.robjects.conversion import localconverter

# 激活自动转换
pandas2ri.activate()

# 创建Pandas DataFrame
py_df = pd.DataFrame({
    'id': [1, 2, 3],
    'value': [4.5, 6.7, 8.9],
    'category': ['A', 'B', 'A']
})

# 转换到R的data.frame
with localconverter(robjects.default_converter + pandas2ri.converter):
    r_df = robjects.conversion.py2rpy(py_df)

# 在R中处理数据
robjects.r('''
    process_data <- function(df) {
        # 计算每组的平均值
        result <- aggregate(value ~ category, data=df, FUN=mean)
        return(result)
    }
''')

# 获取R函数
r_process = robjects.globalenv['process_data']

# 调用函数并获取结果
result_r = r_process(r_df)

# 转换回Pandas DataFrame
with localconverter(robjects.default_converter + pandas2ri.converter):
    result_py = robjects.conversion.rpy2py(result_r)

print("在Python中处理的结果：")
print(result_py)

from rpy2.robjects.packages import importr
import rpy2.robjects.lib.ggplot2 as ggplot2

# 导入R包
ggplot2 = importr('ggplot2')
grdevices = importr('grDevices')

# 创建示例数据
df = robjects.DataFrame({
    "x": robjects.IntVector([1, 2, 3, 4, 5]),
    "y": robjects.FloatVector([2.1, 3.5, 4.9, 5.7, 7.2]),
    "group": robjects.StrVector(["A", "A", "B", "B", "A"])
})

# 创建ggplot对象
plot = (ggplot2.ggplot(df) + 
        ggplot2.aes_string(x='x', y='y', color='group') + 
        ggplot2.geom_point(size=4) + 
        ggplot2.geom_smooth(method='lm') + 
        ggplot2.labs(title='Python调用R的ggplot2', 
                    x='X轴', 
                    y='Y轴') + 
        ggplot2.theme_bw())

# 保存图像
grdevices.png(file="r_plot_from_python.png", width=800, height=600)
plot.plot()
grdevices.dev_off()

print("使用ggplot2创建的图表已保存为 r_plot_from_python.png")

生成的图表示例

# 使用Python生成数据
import numpy as np
np.random.seed(42)
group_a = np.random.normal(5.0, 1.5, 50)
group_b = np.random.normal(6.5, 1.2, 50)

# 转换到R
with localconverter(robjects.default_converter + pandas2ri.converter):
    r_group_a = robjects.converter.py2rpy(group_a)
    r_group_b = robjects.converter.py2rpy(group_b)

# 执行t检验
t_test = robjects.r['t.test']
result = t_test(r_group_a, r_group_b)

# 提取结果
p_value = result.rx2('p.value')[0]
print(f"t检验p值: {p_value:.4f}")

# 使用R的lm进行线性回归
robjects.r('''
    perform_regression <- function(x, y) {
        model <- lm(y ~ x)
        return(summary(model))
    }
''')

regression = robjects.globalenv['perform_regression']
x = robjects.FloatVector(np.arange(50))
y = robjects.FloatVector(group_a)

reg_result = regression(x, y)
print("回归模型摘要:")
print(reg_result)

输出示例：