Mission Assignment 2 - Prediction and Machine Learning

import pandas as pd

# GitHub URL for the CSV file (raw format)
url = "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/master/inst/extdata/penguins.csv"

# Load the dataset into a pandas DataFrame
penguins = pd.read_csv(url)

# Display the variable (column) names
print("Variable (column) names in the Palmer Penguins dataset:")
print(penguins.columns.tolist())

pip install plotly

import plotly

import pandas as pd

# GitHub URL for the CSV file (raw format)
url = "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/master/inst/extdata/penguins.csv"

# Load the dataset into a pandas DataFrame
penguins = pd.read_csv(url)

# Display the variable (column) names
print("Variable (column) names in the Palmer Penguins dataset:")
print(penguins.columns.tolist())

print(penguins.head(10))

column_names_list = penguins.columns.tolist()
print("Column names (as a list using .tolist()):")
print(column_names_list)

import pandas as pd
import matplotlib.pyplot as plt

# Load dataset
url = "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/master/inst/extdata/penguins.csv"
penguins = pd.read_csv(url)

# Drop rows with missing values in selected columns
penguins = penguins[['species', 'bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g']].dropna()

# Set style
plt.style.use('seaborn-v0_8-whitegrid')

# 1. Scatter Plot: Bill Length vs Bill Depth
plt.figure(figsize=(8, 6))
for species in penguins['species'].unique():
    subset = penguins[penguins['species'] == species]
    plt.scatter(subset['bill_length_mm'], subset['bill_depth_mm'], label=species, alpha=0.7)
plt.xlabel("Bill Length (mm)")
plt.ylabel("Bill Depth (mm)")
plt.title("Bill Length vs Bill Depth by Species")
plt.legend()
plt.tight_layout()
plt.show()

# 2. Box Plot: Flipper Length by Species
plt.figure(figsize=(8, 6))
penguins.boxplot(column='flipper_length_mm', by='species')
plt.title("Flipper Length by Species")
plt.suptitle('')
plt.xlabel("Species")
plt.ylabel("Flipper Length (mm)")
plt.tight_layout()
plt.show()

# 3. Scatter Plot: Flipper Length vs Body Mass
plt.figure(figsize=(8, 6))
for species in penguins['species'].unique():
    subset = penguins[penguins['species'] == species]
    plt.scatter(subset['flipper_length_mm'], subset['body_mass_g'], label=species, alpha=0.7)
plt.xlabel("Flipper Length (mm)")
plt.ylabel("Body Mass (g)")
plt.title("Flipper Length vs Body Mass by Species")
plt.legend()
plt.tight_layout()
plt.show()

import pandas as pd
import plotly.express as px
import plotly.io as pio
import os

# --- Detect if in Jupyter Notebook ---
try:
    shell = get_ipython().__class__.__name__
    if "ZMQInteractiveShell" in shell:
        pio.renderers.default = 'notebook'  # Jupyter Notebook
    else:
        pio.renderers.default = 'iframe'    # Other notebook-like interface
except NameError:
    # Not in Jupyter (likely script or terminal)
    try:
        pio.renderers.default = 'browser'
    except:
        pio.renderers.default = 'svg'

# --- Load dataset ---
url = "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/master/inst/extdata/penguins.csv"
penguins = pd.read_csv(url)

# --- Clean data ---
penguins = penguins[['species', 'bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g']].dropna()

# --- Plot 1: Bill Length vs Bill Depth ---
fig1 = px.scatter(
    penguins,
    x='bill_length_mm',
    y='bill_depth_mm',
    color='species',
    title='Bill Length vs Bill Depth by Species',
    labels={'bill_length_mm': 'Bill Length (mm)', 'bill_depth_mm': 'Bill Depth (mm)'}
)

# --- Plot 2: Flipper Length by Species (Box Plot) ---
fig2 = px.box(
    penguins,
    x='species',
    y='flipper_length_mm',
    color='species',
    title='Flipper Length by Species',
    labels={'flipper_length_mm': 'Flipper Length (mm)'}
)

# --- Plot 3: Flipper Length vs Body Mass ---
fig3 = px.scatter(
    penguins,
    x='flipper_length_mm',
    y='body_mass_g',
    color='species',
    title='Flipper Length vs Body Mass by Species',
    labels={'flipper_length_mm': 'Flipper Length (mm)', 'body_mass_g': 'Body Mass (g)'}
)

# --- Show or Save Plots Based on Environment ---
try:
    # Try to show plots interactively
    fig1.show()
    fig2.show()
    fig3.show()
except:
    # If that fails (e.g., headless), save as HTML
    print("Interactive display failed. Saving plots as HTML...")
    fig1.write_html("fig1_bill_vs_depth.html")
    fig2.write_html("fig2_flipper_box.html")
    fig3.write_html("fig3_flipper_vs_mass.html")
    print("Plots saved in current directory.")

import pandas as pd
import plotly.express as px
import plotly.io as pio
from IPython.display import HTML, display

# Load and clean data
url = "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/master/inst/extdata/penguins.csv"
penguins = pd.read_csv(url)
penguins = penguins[['species', 'bill_length_mm', 'bill_depth_mm']].dropna()

# Create plot
fig = px.scatter(
    penguins,
    x='bill_length_mm',
    y='bill_depth_mm',
    color='species',
    title='Bill Length vs Bill Depth by Species'
)

# Convert Plotly figure to HTML string
html_plot = pio.to_html(fig, full_html=False, include_plotlyjs='cdn')

# Display using IPython
display(HTML(html_plot))

fig.write_html("my_plot.html")
#<iframe src="my_plot.html" width="100%" height="500px"></iframe>

# 📌 Step 1: Import Libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.preprocessing import LabelEncoder

# 📌 Step 2: Load Palmer Penguins Dataset
url = "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/master/inst/extdata/penguins.csv"
penguins = pd.read_csv(url)

# Drop rows with missing values
penguins.dropna(inplace=True)

# Display first few rows
penguins.head()

# 📌 Step 3: Exploratory Data Analysis (Optional but helpful)
sns.pairplot(penguins, hue="species")
plt.suptitle("Penguin Feature Distributions by Species", y=1.02)
plt.show()

# 📌 Step 4: Preprocessing
# Encode categorical features: 'island', 'sex', and target 'species'

le_species = LabelEncoder()
penguins['species_label'] = le_species.fit_transform(penguins['species'])

le_island = LabelEncoder()
penguins['island_label'] = le_island.fit_transform(penguins['island'])

le_sex = LabelEncoder()
penguins['sex_label'] = le_sex.fit_transform(penguins['sex'])

# Define features and target
features = ['bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g', 'island_label', 'sex_label']
target = 'species_label'

# 📌 Step 5: Train-Test Split
X = penguins[features]
y = penguins[target]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 📌 Step 6: Train Random Forest Classifier
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Predict
y_pred = model.predict(X_test)

# 📌 Step 7: Evaluate Model
print("Classification Report:\n", classification_report(y_test, y_pred, target_names=le_species.classes_))

# Confusion Matrix
conf_matrix = confusion_matrix(y_test, y_pred)
sns.heatmap(conf_matrix, annot=True, fmt='d', xticklabels=le_species.classes_, yticklabels=le_species.classes_)
plt.title("Confusion Matrix")
plt.xlabel("Predicted")
plt.ylabel("Actual")
plt.show()

# 📌 Step 8: Feature Importance
importances = model.feature_importances_
feature_names = X.columns

plt.figure(figsize=(8, 6))
sns.barplot(x=importances, y=feature_names)
plt.title("Feature Importances in Penguin Classification")
plt.show()