R to Python Converter

library(dplyr)

# R dataframe with dplyr pipeline
employees <- data.frame(
  name = c("Alice", "Bob", "Charlie", "Diana"),
  age = c(28, 35, 42, 31),
  salary = c(65000, 75000, 85000, 70000),
  department = c("Sales", "IT", "IT", "Sales")
)

# dplyr pipeline with %>%
result <- employees %>%
  filter(age > 30) %>%
  mutate(salary_increase = salary * 1.1) %>%
  select(name, age, salary_increase, department) %>%
  arrange(desc(salary_increase))

# Column access with $
avg_salary <- mean(employees$salary)

# Grouping and summarization
dept_summary <- employees %>%
  group_by(department) %>%
  summarise(
    avg_age = mean(age),
    total_salary = sum(salary),
    count = n()
  )

print(result)

import pandas as pd

# Python dataframe with pandas
employees = pd.DataFrame({
    'name': ['Alice', 'Bob', 'Charlie', 'Diana'],
    'age': [28, 35, 42, 31],
    'salary': [65000, 75000, 85000, 70000],
    'department': ['Sales', 'IT', 'IT', 'Sales']
})

# pandas method chaining (replaces %>%)
result = (employees
    .query('age > 30')
    .assign(salary_increase=lambda df: df['salary'] * 1.1)
    [['name', 'age', 'salary_increase', 'department']]
    .sort_values('salary_increase', ascending=False)
)

# Column access with bracket notation
avg_salary = employees['salary'].mean()

# Grouping and aggregation
dept_summary = (employees
    .groupby('department')
    .agg(
        avg_age=('age', 'mean'),
        total_salary=('salary', 'sum'),
        count=('name', 'size')
    )
)

print(result)

library(ggplot2)

# R visualization with ggplot2
data <- data.frame(
  x = 1:100,
  y = rnorm(100, mean = 50, sd = 10),
  category = rep(c("A", "B"), each = 50)
)

# ggplot2 with grammar of graphics
plot <- ggplot(data, aes(x = x, y = y, color = category)) +
  geom_point(size = 3, alpha = 0.6) +
  geom_smooth(method = "lm", se = TRUE) +
  facet_wrap(~ category) +
  labs(
    title = "Scatter Plot by Category",
    x = "X Values",
    y = "Y Values"
  ) +
  theme_minimal()

# Display plot
print(plot)

# Statistical test
t_test_result <- t.test(y ~ category, data = data)
print(t_test_result)

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats

# Python visualization with matplotlib/seaborn
np.random.seed(42)
data = pd.DataFrame({
    'x': range(1, 101),
    'y': np.random.normal(50, 10, 100),
    'category': ['A'] * 50 + ['B'] * 50
})

# Create subplots for faceting
fig, axes = plt.subplots(1, 2, figsize=(12, 5))

# Plot for each category
for idx, category in enumerate(['A', 'B']):
    cat_data = data[data['category'] == category]
    
    # Scatter plot with regression line
    axes[idx].scatter(cat_data['x'], cat_data['y'], 
                      s=50, alpha=0.6, label=category)
    
    # Add regression line
    z = np.polyfit(cat_data['x'], cat_data['y'], 1)
    p = np.poly1d(z)
    axes[idx].plot(cat_data['x'], p(cat_data['x']), 
                   'r-', alpha=0.8)
    
    axes[idx].set_title(f'Category {category}')
    axes[idx].set_xlabel('X Values')
    axes[idx].set_ylabel('Y Values')
    axes[idx].legend()

plt.suptitle('Scatter Plot by Category')
plt.tight_layout()
plt.show()

# Statistical test
category_a = data[data['category'] == 'A']['y']
category_b = data[data['category'] == 'B']['y']
t_test_result = stats.ttest_ind(category_a, category_b)
print(f"T-statistic: {t_test_result.statistic}, P-value: {t_test_result.pvalue}")