数据星期二

TidyTuesday data project

data from github

getting the data

R

#pak::pak('tidytuesdayR')

library(tidytuesdayR)
library(tidyverse)

download the data

all available data

#tt_available() 

tuesdata <- tidytuesdayR::tt_load('2025-04-01')

tuesdata

Python

import pandas as pd
import pydytuesday

pydytuesday.get_date('2025-04-15')

Trying to fetch README from: https://raw.githubusercontent.com/rfordatascience/tidytuesday/refs/heads/main/data/2025/2025-04-15/readme.md
Successfully fetched README from: https://raw.githubusercontent.com/rfordatascience/tidytuesday/refs/heads/main/data/2025/2025-04-15/readme.md
Downloading meta.yaml...
Successfully saved meta.yaml to /Users/jinchaoduan/Documents/Project/Tech blog/posts/TidyTuesday/meta.yaml
Downloading penguins.csv...
Successfully saved penguins.csv to /Users/jinchaoduan/Documents/Project/Tech blog/posts/TidyTuesday/penguins.csv
Downloading penguins_raw.csv...
Successfully saved penguins_raw.csv to /Users/jinchaoduan/Documents/Project/Tech blog/posts/TidyTuesday/penguins_raw.csv

make a shiny

R

read data

data=tuesdata$pokemon_df
#glimpse(data)

or read directly from the url

data<- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-04-01/pokemon_df.csv')

using shinyapps assistant to create shinyapp

https://gallery.shinyapps.io/assistant

go to project folder and install quarto-ext/shinylive

quarto add quarto-ext/shinylive

Prompt:

create a shinyapp with this data from github:https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-04-01/pokemon_df.csv. left side: selector type_1 number of pokemon right side: histogram of height, color by type_2 histogram of weight, color by type_2 histogram of attack, color by type_2 histogram of defense color by type_2 barplot of color_1

there is no weight_kg,height_m.please use correct name.

Shiny R in quarto

if adding shiny in quarto then adding this to yaml header

---

filters:
  - shinylive
---

library(shiny)
library(bslib)
library(tidyverse)
library(ggplot2)

# Load the Pokemon data
pokemon_data <- read.csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-04-01/pokemon_df.csv")

ui <- page_sidebar(
  title = "Pokemon Data Explorer",
  sidebar = sidebar(
    selectInput("type1", "Select Type 1:", 
                choices = sort(unique(pokemon_data$type_1)),
                selected = "water"),
    hr(),
    textOutput("pokemon_count")
  ),
  
  layout_columns(
    card(
      card_header("Height Distribution by Type 2"),
      plotOutput("height_hist")
    ),
    card(
      card_header("Weight Distribution by Type 2"),
      plotOutput("weight_hist")
    )
  ),
  
  layout_columns(
    card(
      card_header("Attack Distribution by Type 2"),
      plotOutput("attack_hist")
    ),
    card(
      card_header("Defense Distribution by Type 2"),
      plotOutput("defense_hist")
    )
  ),
  
  card(
    card_header("Pokemon Color Distribution"),
    plotOutput("color_barplot")
  )
)

server <- function(input, output, session) {
  
  # Filtered data based on the selected type_1
  filtered_data <- reactive({
    pokemon_data %>%
      filter(type_1 == input$type1)
  })
  
  # Display number of Pokemon
  output$pokemon_count <- renderText({
    count <- nrow(filtered_data())
    paste("Number of Pokemon with Type 1 '", input$type1, "': ", count)
  })
  
  # Height histogram colored by type_2
  output$height_hist <- renderPlot({
    ggplot(filtered_data(), aes(x = height, fill = type_2)) +
      geom_histogram(alpha = 0.7, bins = 20, position = "identity") +
      scale_fill_viridis_d() +
      theme_minimal() +
      labs(x = "Height", y = "Count", fill = "Type 2")
  })
  
  # Weight histogram colored by type_2
  output$weight_hist <- renderPlot({
    ggplot(filtered_data(), aes(x = weight, fill = type_2)) +
      geom_histogram(alpha = 0.7, bins = 20, position = "identity") +
      scale_fill_viridis_d() +
      theme_minimal() +
      labs(x = "Weight", y = "Count", fill = "Type 2")
  })
  
  # Attack histogram colored by type_2
  output$attack_hist <- renderPlot({
    ggplot(filtered_data(), aes(x = attack, fill = type_2)) +
      geom_histogram(alpha = 0.7, bins = 20, position = "identity") +
      scale_fill_viridis_d() +
      theme_minimal() +
      labs(x = "Attack", y = "Count", fill = "Type 2")
  })
  
  # Defense histogram colored by type_2
  output$defense_hist <- renderPlot({
    ggplot(filtered_data(), aes(x = defense, fill = type_2)) +
      geom_histogram(alpha = 0.7, bins = 20, position = "identity") +
      scale_fill_viridis_d() +
      theme_minimal() +
      labs(x = "Defense", y = "Count", fill = "Type 2")
  })
  
  # Barplot of color_1
  output$color_barplot <- renderPlot({
    color_counts <- filtered_data() %>%
      count(color_1) %>%
      arrange(desc(n))
    
    ggplot(color_counts, aes(x = reorder(color_1, n), y = n, fill = color_1)) +
      geom_col() +
      coord_flip() +
      scale_fill_brewer(palette = "Set3") +
      theme_minimal() +
      labs(x = "Color", y = "Count", fill = "Color") +
      theme(legend.position = "none")
  })
}

shinyApp(ui, server)

#| '!! shinylive warning !!': |
#|   shinylive does not work in self-contained HTML documents.
#|   Please set `embed-resources: false` in your metadata.
#| standalone: true
#| viewerHeight: 800
library(shiny)
library(bslib)
library(tidyverse)
library(ggplot2)

# Load the Pokemon data
pokemon_data <- read.csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-04-01/pokemon_df.csv")

ui <- page_sidebar(
  title = "Pokemon Data Explorer",
  sidebar = sidebar(
    selectInput("type1", "Select Type 1:", 
                choices = sort(unique(pokemon_data$type_1)),
                selected = "water"),
    hr(),
    textOutput("pokemon_count")
  ),
  
  layout_columns(
    card(
      card_header("Height Distribution by Type 2"),
      plotOutput("height_hist")
    ),
    card(
      card_header("Weight Distribution by Type 2"),
      plotOutput("weight_hist")
    )
  ),
  
  layout_columns(
    card(
      card_header("Attack Distribution by Type 2"),
      plotOutput("attack_hist")
    ),
    card(
      card_header("Defense Distribution by Type 2"),
      plotOutput("defense_hist")
    )
  ),
  
  card(
    card_header("Pokemon Color Distribution"),
    plotOutput("color_barplot")
  )
)

server <- function(input, output, session) {
  
  # Filtered data based on the selected type_1
  filtered_data <- reactive({
    pokemon_data %>%
      filter(type_1 == input$type1)
  })
  
  # Display number of Pokemon
  output$pokemon_count <- renderText({
    count <- nrow(filtered_data())
    paste("Number of Pokemon with Type 1 '", input$type1, "': ", count)
  })
  
  # Height histogram colored by type_2
  output$height_hist <- renderPlot({
    ggplot(filtered_data(), aes(x = height, fill = type_2)) +
      geom_histogram(alpha = 0.7, bins = 20, position = "identity") +
      scale_fill_viridis_d() +
      theme_minimal() +
      labs(x = "Height", y = "Count", fill = "Type 2")
  })
  
  # Weight histogram colored by type_2
  output$weight_hist <- renderPlot({
    ggplot(filtered_data(), aes(x = weight, fill = type_2)) +
      geom_histogram(alpha = 0.7, bins = 20, position = "identity") +
      scale_fill_viridis_d() +
      theme_minimal() +
      labs(x = "Weight", y = "Count", fill = "Type 2")
  })
  
  # Attack histogram colored by type_2
  output$attack_hist <- renderPlot({
    ggplot(filtered_data(), aes(x = attack, fill = type_2)) +
      geom_histogram(alpha = 0.7, bins = 20, position = "identity") +
      scale_fill_viridis_d() +
      theme_minimal() +
      labs(x = "Attack", y = "Count", fill = "Type 2")
  })
  
  # Defense histogram colored by type_2
  output$defense_hist <- renderPlot({
    ggplot(filtered_data(), aes(x = defense, fill = type_2)) +
      geom_histogram(alpha = 0.7, bins = 20, position = "identity") +
      scale_fill_viridis_d() +
      theme_minimal() +
      labs(x = "Defense", y = "Count", fill = "Type 2")
  })
  
  # Barplot of color_1
  output$color_barplot <- renderPlot({
    color_counts <- filtered_data() %>%
      count(color_1) %>%
      arrange(desc(n))
    
    ggplot(color_counts, aes(x = reorder(color_1, n), y = n, fill = color_1)) +
      geom_col() +
      coord_flip() +
      scale_fill_brewer(palette = "Set3") +
      theme_minimal() +
      labs(x = "Color", y = "Count", fill = "Color") +
      theme(legend.position = "none")
  })
}

shinyApp(ui, server)

Python

install shiny in python

Need to down grade shinylive Python version to 0.7.1 in order to match shinylive R version

import os
os.system("pip install 'shinylive==0.7.1'")

read data

penguins = pd.read_csv('penguins.csv')
penguins_raw = pd.read_csv('penguins_raw.csv')

# Option 2: Read directly from GitHub and assign to an object
#penguins = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-04-15/penguins.csv')
#penguins_raw = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-04-15/penguins_raw.csv')

using shinyapps assistant to create shinyapp

https://gallery.shinyapps.io/assistant

install shinylive

pip install shinylive

Prompt:

create a shinyapp with this data from github:https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-04-15/penguins_raw.csv.

species choices is not correct,please use correct choices.

Shiny Python in quarto

if adding shiny in quarto then adding this to yaml header

---

filters:
  - shinylive
---

from shiny import App, reactive, render, ui
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import urllib3

app_ui = ui.page_sidebar(
    ui.sidebar(
        ui.h3("Penguin Data Explorer"),
        ui.input_select(
            "species",
            "Select Penguin Species",
            choices=["All Species", "Adelie Penguin (Pygoscelis adeliae)", 
                     "Gentoo penguin (Pygoscelis papua)", 
                     "Chinstrap penguin (Pygoscelis antarctica)"]
        ),
        ui.input_select(
            "plot_type",
            "Select Plot Type",
            choices=[
                "Body Mass vs Flipper Length",
                "Culmen Length vs Depth",
                "Histogram of Body Mass"
            ]
        ),
        ui.input_checkbox_group(
            "islands",
            "Select Islands",
            choices=["Torgersen", "Biscoe", "Dream"],
            selected=["Torgersen", "Biscoe", "Dream"]
        ),
        ui.hr(),
        ui.p("Data from Palmer Penguins dataset via TidyTuesday."),
    ),
    ui.card(
        ui.card_header("Penguin Data Visualization"),
        ui.output_plot("penguin_plot")
    ),
    ui.card(
        ui.card_header("Data Summary"),
        ui.output_table("summary_table")
    )
)

def server(input, output, session):
    # Load data
    @reactive.calc
    def load_data():
        http = urllib3.PoolManager()
        url = "https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-04-15/penguins_raw.csv"
        
        try:
            response = http.request('GET', url)
            if response.status != 200:
                # If file not found, use fallback URL
                fallback_url = "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/main/inst/extdata/penguins_raw.csv"
                response = http.request('GET', fallback_url)
                
            data = pd.read_csv(pd.io.common.StringIO(response.data.decode('utf-8')))
            return data
        except Exception as e:
            print(f"Error loading data: {e}")
            # Return empty dataframe if there are issues
            return pd.DataFrame()

    @reactive.calc
    def filtered_data():
        data = load_data()
        if data.empty:
            return pd.DataFrame()
        
        # Clean column names
        data.columns = [col.strip() for col in data.columns]
        
        # Filter data based on inputs
        filtered = data.copy()
        
        # Filter by species
        if input.species() != "All Species":
            filtered = filtered[filtered['Species'] == input.species()]
        
        # Filter by islands
        filtered = filtered[filtered['Island'].isin(input.islands())]
        
        return filtered

    @output
    @render.plot
    def penguin_plot():
        data = filtered_data()
        if data.empty:
            fig, ax = plt.subplots()
            ax.text(0.5, 0.5, "No data available or error loading data", 
                    ha='center', va='center')
            ax.set_xlim(0, 1)
            ax.set_ylim(0, 1)
            ax.axis('off')
            return fig
        
        fig, ax = plt.subplots(figsize=(10, 6))
        
        plot_type = input.plot_type()
        
        if plot_type == "Body Mass vs Flipper Length":
            sns.scatterplot(
                data=data, 
                x='Flipper Length (mm)', 
                y='Body Mass (g)',
                hue='Species',
                style='Sex',
                ax=ax
            )
            ax.set_title("Body Mass vs Flipper Length")
            
        elif plot_type == "Culmen Length vs Depth":
            sns.scatterplot(
                data=data, 
                x='Culmen Length (mm)', 
                y='Culmen Depth (mm)',
                hue='Species',
                style='Sex',
                ax=ax
            )
            ax.set_title("Culmen Length vs Depth")
            
        elif plot_type == "Histogram of Body Mass":
            sns.histplot(
                data=data,
                x='Body Mass (g)',
                hue='Species',
                kde=True,
                ax=ax
            )
            ax.set_title("Distribution of Body Mass")
            
        plt.tight_layout()
        return fig

    @output
    @render.table
    def summary_table():
        data = filtered_data()
        if data.empty:
            return pd.DataFrame({'Message': ['No data available or error loading data']})
        
        # Create a summary table with counts by species and island
        summary = data.groupby(['Species', 'Island', 'Sex']).size().reset_index(name='Count')
        
        # Add some descriptive statistics
        stats = data.groupby(['Species']).agg({
            'Body Mass (g)': ['mean', 'std'],
            'Flipper Length (mm)': ['mean', 'std'],
            'Culmen Length (mm)': ['mean', 'std'],
            'Culmen Depth (mm)': ['mean', 'std']
        }).round(2)
        
        stats.columns = ['_'.join(col).strip() for col in stats.columns.values]
        stats = stats.reset_index()
        
        return summary

app = App(app_ui, server)

#| '!! shinylive warning !!': |
#|   shinylive does not work in self-contained HTML documents.
#|   Please set `embed-resources: false` in your metadata.
#| standalone: true
#| viewerHeight: 800
from shiny import App, reactive, render, ui
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import urllib3

app_ui = ui.page_sidebar(
    ui.sidebar(
        ui.h3("Penguin Data Explorer"),
        ui.input_select(
            "species",
            "Select Penguin Species",
            choices=["All Species", "Adelie Penguin (Pygoscelis adeliae)", 
                     "Gentoo penguin (Pygoscelis papua)", 
                     "Chinstrap penguin (Pygoscelis antarctica)"]
        ),
        ui.input_select(
            "plot_type",
            "Select Plot Type",
            choices=[
                "Body Mass vs Flipper Length",
                "Culmen Length vs Depth",
                "Histogram of Body Mass"
            ]
        ),
        ui.input_checkbox_group(
            "islands",
            "Select Islands",
            choices=["Torgersen", "Biscoe", "Dream"],
            selected=["Torgersen", "Biscoe", "Dream"]
        ),
        ui.hr(),
        ui.p("Data from Palmer Penguins dataset via TidyTuesday."),
    ),
    ui.card(
        ui.card_header("Penguin Data Visualization"),
        ui.output_plot("penguin_plot")
    ),
    ui.card(
        ui.card_header("Data Summary"),
        ui.output_table("summary_table")
    )
)

def server(input, output, session):
    # Load data
    @reactive.calc
    def load_data():
        http = urllib3.PoolManager()
        url = "https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-04-15/penguins_raw.csv"
        
        try:
            response = http.request('GET', url)
            if response.status != 200:
                # If file not found, use fallback URL
                fallback_url = "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/main/inst/extdata/penguins_raw.csv"
                response = http.request('GET', fallback_url)
                
            data = pd.read_csv(pd.io.common.StringIO(response.data.decode('utf-8')))
            return data
        except Exception as e:
            print(f"Error loading data: {e}")
            # Return empty dataframe if there are issues
            return pd.DataFrame()

    @reactive.calc
    def filtered_data():
        data = load_data()
        if data.empty:
            return pd.DataFrame()
        
        # Clean column names
        data.columns = [col.strip() for col in data.columns]
        
        # Filter data based on inputs
        filtered = data.copy()
        
        # Filter by species
        if input.species() != "All Species":
            filtered = filtered[filtered['Species'] == input.species()]
        
        # Filter by islands
        filtered = filtered[filtered['Island'].isin(input.islands())]
        
        return filtered

    @output
    @render.plot
    def penguin_plot():
        data = filtered_data()
        if data.empty:
            fig, ax = plt.subplots()
            ax.text(0.5, 0.5, "No data available or error loading data", 
                    ha='center', va='center')
            ax.set_xlim(0, 1)
            ax.set_ylim(0, 1)
            ax.axis('off')
            return fig
        
        fig, ax = plt.subplots(figsize=(10, 6))
        
        plot_type = input.plot_type()
        
        if plot_type == "Body Mass vs Flipper Length":
            sns.scatterplot(
                data=data, 
                x='Flipper Length (mm)', 
                y='Body Mass (g)',
                hue='Species',
                style='Sex',
                ax=ax
            )
            ax.set_title("Body Mass vs Flipper Length")
            
        elif plot_type == "Culmen Length vs Depth":
            sns.scatterplot(
                data=data, 
                x='Culmen Length (mm)', 
                y='Culmen Depth (mm)',
                hue='Species',
                style='Sex',
                ax=ax
            )
            ax.set_title("Culmen Length vs Depth")
            
        elif plot_type == "Histogram of Body Mass":
            sns.histplot(
                data=data,
                x='Body Mass (g)',
                hue='Species',
                kde=True,
                ax=ax
            )
            ax.set_title("Distribution of Body Mass")
            
        plt.tight_layout()
        return fig

    @output
    @render.table
    def summary_table():
        data = filtered_data()
        if data.empty:
            return pd.DataFrame({'Message': ['No data available or error loading data']})
        
        # Create a summary table with counts by species and island
        summary = data.groupby(['Species', 'Island', 'Sex']).size().reset_index(name='Count')
        
        # Add some descriptive statistics
        stats = data.groupby(['Species']).agg({
            'Body Mass (g)': ['mean', 'std'],
            'Flipper Length (mm)': ['mean', 'std'],
            'Culmen Length (mm)': ['mean', 'std'],
            'Culmen Depth (mm)': ['mean', 'std']
        }).round(2)
        
        stats.columns = ['_'.join(col).strip() for col in stats.columns.values]
        stats = stats.reset_index()
        
        return summary

app = App(app_ui, server)

Reference

https://github.com/rfordatascience/tidytuesday

https://github.com/posit-dev/python-tidytuesday