Competition - Everyone Can Learn Data Scholarship

# Run this cell to see the result (click on Run on the right, or Ctrl|CMD + Enter)
100 * 1.75 * 20

# Import the pandas and numpy packages
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import folium


# Load the data
dinosaurs = pd.read_csv('data/dinosaurs.csv')
dinosaur_names = dinosaurs['name']

# How many different dinosaur names are present in the data?
unique_dinosaur_names = dinosaur_names.nunique()
print(f'The number of unique dinosaur names is: {unique_dinosaur_names}')

#Which was the largest dinosaur? What about missing data in the dataset?
print(dinosaurs.head())
dinosaurs.dropna(subset=['name'], inplace=True)

# Drop rows where 'length' is missing
dinosaurs.dropna(subset=['length_m'], inplace=True)

# Ensure the 'length' columns are numeric
dinosaurs['length_m'] = pd.to_numeric(dinosaurs['length_m'], errors='coerce')

# Determine the largest dinosaur based on length
largest_dinosaur_by_length = dinosaurs.loc[dinosaurs['length_m'].idxmax()]
print(f"The largest dinosaur by length is {largest_dinosaur_by_length['name']} with a length of {largest_dinosaur_by_length['length_m']} meters.")

# Count occurrences by dinosaur type
dinosaur_type_counts = dinosaurs['type'].value_counts()

# Create a bar chart
plt.figure(figsize=(12, 8))
bars = plt.bar(dinosaur_type_counts.index, dinosaur_type_counts.values, color='seagreen')

# Add labels and title
plt.xlabel('Dinosaur Type', fontsize=14)
plt.ylabel('Number of Occurrences', fontsize=14)
plt.title('Number of Dinosaurs per type', fontsize=16)

# Customize the x-axis and y-axis labels
plt.xticks(rotation=45, ha='right', fontsize=12)
plt.yticks(fontsize=12)

# Add a grid for better readability
plt.grid(axis='y', linestyle='--', alpha=0.7)

# Add the counts above the bars
for bar in bars:
    height = bar.get_height()
    plt.text(bar.get_x() + bar.get_width() / 2.0, height, f'{int(height)}', ha='center', va='bottom', fontsize=12)

# Show the plot
plt.tight_layout()
plt.show()


#What dinosaur type has the most occurrences in this dataset? Create a visualization (table, bar chart, or equivalent) to display the number of dinosaurs per type. Use the AI assistant to tweak your visualization (colors, labels, title...).
#Did dinosaurs get bigger over time? Show the relation between the dinosaur length and their age to illustrate this.

class_to_age = {
    'Saurischia': 150,  # Midpoint for late Jurassic to early Cretaceous
    'Ornithischia': 100, # Midpoint for late Jurassic to late Cretaceous
    'Theropoda': 130,   # Spanning Triassic to Cretaceous
    'Sauropoda': 160    # Mostly in the Jurassic period
}

# Map the dinosaur classes to ages
dinosaurs['age'] = dinosaurs['class'].map(class_to_age)

# Handle missing data
# Drop rows where 'name', 'length', or 'age' is missing
dinosaurs.dropna(subset=['name', 'length_m', 'age'], inplace=True)

# Ensure the 'length' and 'age' columns are numeric
dinosaurs['length_m'] = pd.to_numeric(dinosaurs['length_m'], errors='coerce')
dinosaurs['age'] = pd.to_numeric(dinosaurs['age'], errors='coerce')

# Create a scatter plot to show the relationship between length and age
plt.figure(figsize=(12, 8))
sns.scatterplot(data=dinosaurs, x='age', y='length_m', hue='name', palette='viridis', s=100)

# Add labels and title
plt.xlabel('Age (in millions of years)', fontsize=14)
plt.ylabel('Length (in meters)', fontsize=14)
plt.title('Dinosaur Length vs. Age', fontsize=16)

# Show a legend
plt.legend(title='Dinosaur Name', bbox_to_anchor=(1.05, 1), loc='upper left')

# Show the plot
plt.tight_layout()
plt.show()

#Use the AI assitant to create an interactive map showing each record.
import folium

# Create a map object
m = folium.Map(location=[20, 0], zoom_start=2)

# Add points to the map
for idx, row in dinosaurs.iterrows():
    folium.Marker([row['lat'], row['lng']], popup=f"{row['name']} ({row['age']} million years ago)").add_to(m)



#Other Insights 
# Correlation between Length and Age
correlation = dinosaurs['length_m'].corr(dinosaurs['age'])
print(f'Correlation between Length and Age: {correlation}')

# Box Plot of Dinosaur Lengths
plt.figure(figsize=(10, 6))
sns.boxplot(y=dinosaurs['length_m'], color='green')
plt.title('Box Plot of Dinosaur Lengths')
plt.ylabel('Length (in meters)')
plt.show()

# Count of Dinosaurs by Category
# Example categorical column 'class'
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd

# Example dataset
data = {
    'name': ['Tyrannosaurus', 'Diplodocus', 'Triceratops'],
    'class': ['Theropoda', 'Sauropoda', 'Ornithischia']
}

# Creating the DataFrame
dinosaurs = pd.DataFrame(data)

# Plotting the count of dinosaurs by class
plt.figure(figsize=(10, 6))
sns.countplot(x='class', data=dinosaurs, palette='viridis')
plt.title('Count of Dinosaurs by Class')
plt.xlabel('Class')
plt.ylabel('Count')
plt.show()


# Length vs. Age with Regression Line
data = {
    'name': ['Tyrannosaurus', 'Diplodocus', 'Triceratops'],
    'age': [68, 154, 66],  # Age in millions of years
    'length_m': [12.3, 27.0, 9.0]  # Length in meters
}

# Creating the DataFrame
dinosaurs = pd.DataFrame(data)

# Plotting Length vs. Age with Regression Line
plt.figure(figsize=(10, 6))
sns.regplot(x='age', y='length_m', data=dinosaurs, scatter_kws={'s':100}, line_kws={'color':'red'})
plt.title('Dinosaur Length vs. Age with Regression Line')
plt.xlabel('Age (in millions of years)')
plt.ylabel('Length (in meters)')
plt.show()

dinosaurs