Find temporal outliers in FinBIF simple datafile

temporal_outliers.py

# Made with ChatGPT GPT-4 2023-11-23
# Finds temporal outliers from a simple occurrence data file of a single species from FinBIF, with headers in English.

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from shapely.geometry import Point
import geopandas as gpd

# Load the data
file_path = 'single_species_data.tsv'  # Replace with your file path
data = pd.read_csv(file_path, sep='\t')

# Function to find outliers
def find_outliers(df, column):
    Q1 = df[column].quantile(0.25)
    Q3 = df[column].quantile(0.75)
    IQR = Q3 - Q1
    lower_bound = Q1 - 1.5 * IQR
    upper_bound = Q3 + 1.5 * IQR

    outliers = df[(df[column] < lower_bound) | (df[column] > upper_bound)]
    return outliers

# Filter data for specific conditions
filtered_data = data[(data['Life stage'].isna()) | (data['Life stage'] == 'adult')]
filtered_data_same_day = filtered_data[filtered_data['Begin day of year'] == filtered_data['End day of year']]

# Find outliers in the filtered dataset
begin_day_outliers_filtered = find_outliers(filtered_data_same_day, 'Begin day of year')
end_day_outliers_filtered = find_outliers(filtered_data_same_day, 'End day of year')

# Combine the outliers and get unique observation identifiers
outlier_identifiers_filtered = pd.concat([begin_day_outliers_filtered, end_day_outliers_filtered])['Observation identifier'].unique()

print(outlier_identifiers_filtered.tolist())