TidyTuesday dataset of 2025-09-02

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

frogID_data = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-09-02/frogID_data.csv')
frog_names = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-09-02/frog_names.csv')

frogID_data

frog_names

frogID_data['genus'] = frogID_data['scientificName'].str.split(' ').str[0]
frogID_data['species'] = frogID_data['scientificName'].str.split(' ').str[1]
frogID_data

frogID_data.groupby('genus').nunique()['species'].sort_values(ascending=False)

genus
Litoria 64
Uperoleia 21
Crinia 14
Cyclorana 11
Pseudophryne 10
Limnodynastes 10
Mixophyes 8
Cophixalus 7
Neobatrachus 6
Heleioporus 6
Austrochaperina 5
Geocrinia 4
Philoria 4
Platyplectrum 2
Notaden 2
Anstisia 2
Myobatrachus 1
Papurana 1
Paracrinia 1
Metacrinia 1
Lechriodus 1
Assa 1
Rhinella 1
Spicospina 1
Taudactylus 1
Adelotus 1
Name: species, dtype: int64

frogID_data['eventDate'] = pd.to_datetime(frogID_data['eventDate'])
df_grp = frogID_data.groupby('eventDate').nunique().reset_index()
df_grp

aus_seasons = {'Summer': ('2023-01-01', '2023-02-28'),
               'Autumn': ('2023-03-01', '2023-05-31'),
               'Winter': ('2023-06-01', '2023-08-31'),
               'Spring': ('2023-09-01', '2023-11-30')}
fig, ax = plt.subplots(figsize=(8, 4))
plt.rcParams['figure.facecolor'] = '#FFCA99'  # Dark grey figure background
plt.rcParams['axes.facecolor'] = '#FFCA99'  
plt.rcParams['axes.edgecolor'] = '#D69456'
plt.rcParams['xtick.color'] = '#713600'
plt.rcParams['ytick.color'] = '#713600'
plt.rcParams['text.color'] = '#713600'
plt.rcParams['axes.labelcolor'] = '#713600'
plt.rcParams['axes.titlecolor'] = '#713600'


for season, (start, end) in aus_seasons.items():
    if (season == 'Autumn' or season == 'Spring'):
        ax.axvspan(pd.to_datetime(start), pd.to_datetime(end), color='#FFE5B4', alpha=0.3, lw=0)
    ax.text((pd.to_datetime(end) - pd.to_datetime(start)) / 2 + pd.to_datetime(start), 10, season, fontsize=10, ha='center', va='bottom', color='#713600')

sns.scatterplot(data=df_grp, x='eventDate', y='scientificName',alpha=0.75, hue='eventID', \
palette='Greens', edgecolor='none', size='eventID', sizes=(10,100), ax=ax)
sns.despine()
#handles, labels = ax.get_legend_handles_labels()
#ax.legend(handles[::-1], labels[::-1], frameon=False, loc='upper center', title='Sighting Events', title_fontsize='medium')
ax.legend(frameon=False, loc='upper center', title='Sighting Events', title_fontsize='medium')
plt.xlabel('')
plt.ylabel('Number of Species')
plt.title('Timeline of frog sightings in Australia in 2023. \nMost species breed during the rainy season, leading to a \npeak in sightings.', fontsize=14, fontfamily="Serif", \
ha='left', x=0, y=1)

dates = pd.date_range(start='2023-01-01', end='2023-12-31', freq='MS')
labels = ['Jan', '', 'Mar', '', '', 'Jun', '', '', 'Sep', '', '', 'Dec']
# Filter out blank labels
filtered_dates = [date for date, label in zip(dates, labels) if label != '']
filtered_labels = [label for label in labels if label != '']
plt.xticks(filtered_dates, filtered_labels)

#plt.xticks(pd.date_range(start='2023-01-01', end='2023-12-31', freq='MS'), ['Jan', '', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])
plt.savefig("Frogs_AUS.png", dpi=300, bbox_inches='tight')
plt.show()

# count commonName values having Tree in it.
print(frog_names['commonName'].str.contains('Tree').sum())
print(frog_names['commonName'].str.contains('Green').sum())

46
6

from wordcloud import WordCloud
all_cnames = ' '.join(frog_names['commonName'])
# remove frog from all_cnames
all_cnames = all_cnames.replace('Frog', '')
wordcloud = WordCloud(width = 800, height = 800, background_color ='white').generate(all_cnames)

plt.figure(figsize = (8, 8), facecolor = None)
plt.imshow(wordcloud)
plt.axis("off")
plt.tight_layout(pad = 0)