Animals

Visualize the correlation between the various animal attributes such as Maximum longevity in years and Body mass in grams.

Importing libraries and packages

# Mathematical operations and data manipulation
import pandas as pd
import numpy as np

# Plotting
import matplotlib.pyplot as plt

# Warnings
import warnings

warnings.filterwarnings("ignore")

%matplotlib inline

Set paths

# Path to datasets directory
data_path = "./datasets"
# Path to assets directory (for saving results to)
assets_path = "./assets"

Loading dataset

dataset = pd.read_csv(f"{data_path}/anage_data.csv")

Exploring dataset

# Shape of the dataset
print("Shape of the dataset: ", dataset.shape)
# Head
dataset

Shape of the dataset:  (4218, 30)

	Unnamed: 0	HAGRID	Kingdom	Phylum	Class	Order	Family	Genus	Species	Common name	...	Growth rate (1/days)	Maximum longevity (yrs)	Specimen origin	Sample size	Data quality	IMR (per yr)	MRDT (yrs)	Metabolic rate (W)	Body mass (g)	Temperature (K)
0	0	3	Animalia	Arthropoda	Branchiopoda	Diplostraca	Daphniidae	Daphnia	pulicaria	Daphnia	...	NaN	0.19	unknown	medium	acceptable	NaN	NaN	NaN	NaN	NaN
1	1	5	Animalia	Arthropoda	Insecta	Diptera	Drosophilidae	Drosophila	melanogaster	Fruit fly	...	NaN	0.30	captivity	large	acceptable	0.05	0.04	NaN	NaN	NaN
2	2	6	Animalia	Arthropoda	Insecta	Hymenoptera	Apidae	Apis	mellifera	Honey bee	...	NaN	8.00	unknown	medium	acceptable	NaN	NaN	NaN	NaN	NaN
3	3	8	Animalia	Arthropoda	Insecta	Hymenoptera	Formicidae	Cardiocondyla	obscurior	Cardiocondyla obscurior	...	NaN	0.50	captivity	medium	acceptable	NaN	NaN	NaN	NaN	NaN
4	4	9	Animalia	Arthropoda	Insecta	Hymenoptera	Formicidae	Lasius	niger	Black garden ant	...	NaN	28.00	unknown	medium	acceptable	NaN	NaN	NaN	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
4213	4214	4239	Animalia	Porifera	Hexactinellida	Lyssacinosida	Rossellidae	Scolymastra	joubini	Hexactinellid sponge	...	NaN	15000.00	wild	medium	questionable	NaN	NaN	NaN	NaN	NaN
4214	4215	4241	Plantae	Pinophyta	Pinopsida	Pinales	Pinaceae	Pinus	longaeva	Great Basin bristlecone pine	...	NaN	5062.00	wild	medium	acceptable	NaN	999.00	NaN	NaN	NaN
4215	4216	4242	Fungi	Ascomycota	Saccharomycetes	Saccharomycetales	Saccharomycetaceae	Saccharomyces	cerevisiae	Baker's yeast	...	NaN	0.04	captivity	large	acceptable	NaN	NaN	NaN	NaN	NaN
4216	4217	4243	Fungi	Ascomycota	Schizosaccharomycetes	Schizosaccharomycetales	Schizosaccharomycetaceae	Schizosaccharomyces	pombe	Fission yeast	...	NaN	NaN	unknown	small	low	NaN	NaN	NaN	NaN	NaN
4217	4218	4244	Fungi	Ascomycota	Sordariomycetes	Sordariales	Lasiosphaeriaceae	Podospora	anserina	Filamentous fungus	...	NaN	NaN	unknown	small	low	NaN	NaN	NaN	NaN	NaN

4218 rows × 30 columns

Cleaning dataset

dataset.drop(dataset.columns[[0]], axis=1, inplace=True)
dataset.head()

	HAGRID	Kingdom	Phylum	Class	Order	Family	Genus	Species	Common name	Female maturity (days)	...	Growth rate (1/days)	Maximum longevity (yrs)	Specimen origin	Sample size	Data quality	IMR (per yr)	MRDT (yrs)	Metabolic rate (W)	Body mass (g)	Temperature (K)
0	3	Animalia	Arthropoda	Branchiopoda	Diplostraca	Daphniidae	Daphnia	pulicaria	Daphnia	NaN	...	NaN	0.19	unknown	medium	acceptable	NaN	NaN	NaN	NaN	NaN
1	5	Animalia	Arthropoda	Insecta	Diptera	Drosophilidae	Drosophila	melanogaster	Fruit fly	7.0	...	NaN	0.30	captivity	large	acceptable	0.05	0.04	NaN	NaN	NaN
2	6	Animalia	Arthropoda	Insecta	Hymenoptera	Apidae	Apis	mellifera	Honey bee	NaN	...	NaN	8.00	unknown	medium	acceptable	NaN	NaN	NaN	NaN	NaN
3	8	Animalia	Arthropoda	Insecta	Hymenoptera	Formicidae	Cardiocondyla	obscurior	Cardiocondyla obscurior	NaN	...	NaN	0.50	captivity	medium	acceptable	NaN	NaN	NaN	NaN	NaN
4	9	Animalia	Arthropoda	Insecta	Hymenoptera	Formicidae	Lasius	niger	Black garden ant	NaN	...	NaN	28.00	unknown	medium	acceptable	NaN	NaN	NaN	NaN	NaN

5 rows × 29 columns

Preprocessing

# Creating samples containing a body mass and a maximum longevity.
longevity = "Maximum longevity (yrs)"
mass = "Body mass (g)"
data = dataset[np.isfinite(dataset[longevity]) & np.isfinite(dataset[mass])]
# Sorting the data according to the animal class
amphibia = data[data["Class"] == "Amphibia"]
aves = data[data["Class"] == "Aves"]
mammalia = data[data["Class"] == "Mammalia"]
reptilia = data[data["Class"] == "Reptilia"]

Visualisation

# Create figure
plt.figure(figsize=(10, 6), dpi=300)
# Create scatter plot
plt.scatter(amphibia[mass], amphibia[longevity], label="Amphibia")
plt.scatter(aves[mass], aves[longevity], label="Aves")
plt.scatter(mammalia[mass], mammalia[longevity], label="Mammalia")
plt.scatter(reptilia[mass], reptilia[longevity], label="Reptilia")
# Add legend
plt.legend()
# Log scale
ax = plt.gca()
ax.set_xscale("log")
ax.set_yscale("log")
# Add labels
plt.xlabel("Body mass in grams")
plt.ylabel("Maximum longevity in years")
# Show plot
plt.show()