Logistic Regression to Classify Seaweed Farm Harvest Readiness Based on Water Parameters

Project info

• Field of studyFisheries and Marine Science
• LevelUndergraduate thesis (S1)
• Method typeClassification
• Estimated build time± 3 working days
• Toolsscikit-learn LogisticRegression, classification_report, roc_curve, confusion_matrix
• PriceUS$19 - US$125

Research goal

Classify harvest readiness status using the features salinity and water transparency with Logistic Regression and assess its accuracy.

Variables

Example result

• 0.944Accuracy
• 0.962Precision
• 0.926Recall
• 0.943F1-score
• 0.954ROC AUC
• 8.788Odds ratio Salinity

The logistic regression model classifies Harvest readiness status (low/high) from Salinity and Water transparency with test accuracy 0.944, F1 0.943 and AUC 0.954.

Computed from illustrative synthetic data, not from a real study.

About Logistic Regression

Logistic regression models the probability of a binary class from several predictors using the logit link. It suits two-class classification where results need interpretation through odds ratios.

Steps

1. 1Prepare features and a binary label, then split into training and test sets
2. 2Standardise numeric features
3. 3Train LogisticRegression
4. 4Compute accuracy, precision, recall, F1, and AUC on the test set
5. 5Show the confusion matrix and ROC curve
6. 6Compute odds ratios from the coefficients

Assumptions to check

• Binary label and independent observations
• Linear relation between predictors and the log-odds
• Enough events per class and no extreme imbalance

Reading and reporting the results

Report test classification metrics with AUC, then interpret the odds ratio of each predictor. If classes are imbalanced, do not rely on accuracy alone.

Example Python code

A short starting script with this project's variable names. The delivered version is adapted to your data and fully commented.

import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, confusion_matrix, roc_curve, roc_auc_score

rng = np.random.default_rng(11)
n = 400
salinity = rng.normal(0, 1, n)
water_transparency = rng.normal(0, 1, n)
logit = 1.5 * salinity - 1.0 * water_transparency + 0.2
harvest_readiness_status = (rng.random(n) < 1 / (1 + np.exp(-logit))).astype(int)

X = np.column_stack([salinity, water_transparency])
X_tr, X_te, y_tr, y_te = train_test_split(X, harvest_readiness_status, test_size=0.25, stratify=harvest_readiness_status, random_state=11)
clf = make_pipeline(StandardScaler(), LogisticRegression())
clf.fit(X_tr, y_tr)
prob = clf.predict_proba(X_te)[:, 1]
pred = clf.predict(X_te)
print(classification_report(y_te, pred))
print("Confusion matrix:\n", confusion_matrix(y_te, pred))
print("AUC:", round(roc_auc_score(y_te, prob), 3))
print("Odds ratios (per SD):", np.exp(clf[-1].coef_).round(3))

fpr, tpr, _ = roc_curve(y_te, prob)
plt.plot(fpr, tpr, label="ROC")
plt.plot([0, 1], [0, 1], "k--")
plt.xlabel("False positive rate"); plt.ylabel("True positive rate"); plt.legend()
plt.show()

Packages and prices

Choose how much help you need. Each higher package includes everything in the lower ones. Prices exclude 11% VAT.

• Payment: 50% down payment before work starts, balance after the deliverables are handed over
• Tax: Prices exclude 11% VAT
• Data and academic integrity: Results are computed from your own research data; you write and stand behind your manuscript, we help with the analysis and your understanding of it
• Revisions: Up to 2 revisions are included in the price (Package 3: 3 rounds)

Frequently asked questions