Gaius Data Camp Competition submission

# 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
# Load the data
dinosaurs = pd.read_csv('data/dinosaurs.csv')

# Preview the dataframe
dinosaurs

# How many different dinosaur names are present in the data?
count = dinosaurs['name'].unique().size
print("The total number of different dinosaur names in the data = " + str(count) )

# Which was the largest dinosaur? What about missing data in the dataset?
largest_dinosaur = dinosaurs.nlargest(5, ['length_m'])
print(largest_dinosaur)
print("The largest dinosaur is Supersaurus")

dinosaurs[dinosaurs.isnull().any(axis=1)]
dinosaurs_dropped = dinosaurs.dropna()
print(dinosaurs_dropped)

# 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...).
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly as py
import plotly.express as px
import plotly.graph_objects as go

dinosaurs = pd.read_csv('data/dinosaurs.csv')

# Group by dinosaur type and count occurrences
dino_counts = dinosaurs['type'].value_counts().reset_index()
dino_counts.columns = ['type', 'occurrence_no']

fig = plt.figure(figsize=(5, 6))
plt.style.use('fivethirtyeight')
plt.bar(
    x=dino_counts["type"],
    height=dino_counts["occurrence_no"],
    color='purple',         # To set the color of the bars
    edgecolor='black',    # To set the color of the bar edges
    linewidth=1.5,        # To set the width of the bar edges
    alpha=0.8             # To set the transparency of the bars
)

plt.xlabel('Dinosaur Type', fontsize=14, fontweight='bold')  # To set the x-axis label with font size and style
plt.ylabel('Count', fontsize=14, fontweight='bold')           # To set the y-axis label with font size and style
plt.title('Number of Dinosaur Per Type', fontsize=16, fontweight='bold')  # To set the chart title with font size and style
plt.xticks(fontsize=12, rotation = 45)    # To set the font size of the x-axis tick labels
plt.yticks(fontsize=12)    # To set the font size of the y-axis tick labels
plt.grid(True, linestyle='--', linewidth=0.5, alpha=0.5, color = "black")  # To display gridlines with a dashed style and reduced opacity

plt.show()

# Did dinosaurs get bigger over time? Show the relation between the dinosaur length and their age to illustrate this.

import matplotlib.pyplot as plt
import seaborn as sns

# Create a new column for the midpoint of the age range
dinosaurs['mid_ma'] = (dinosaurs['max_ma'] + dinosaurs['min_ma']) / 2

# Plot the relationship between dinosaur length and their age
plt.figure(figsize=(12, 6))
sns.scatterplot(data=dinosaurs, x='mid_ma', y='length_m', hue='type', alpha=0.7)
plt.title('Dinosaur Length Over Time')
plt.xlabel('Age (Ma)')
plt.ylabel('Length (m)')
plt.legend(title='Type')
plt.gca().invert_xaxis()  # Invert x-axis to show time progressing from left to right
plt.show()

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

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

# Create a marker cluster
marker_cluster = MarkerCluster().add_to(m)

# Add markers to the map
for idx, row in dinosaurs.iterrows():
    folium.Marker(
        location=[row['lat'], row['lng']],
        popup=(
            f"<strong>Name:</strong> {row['name']}<br>"
            f"<strong>Type:</strong> {row['type']}<br>"
            f"<strong>Diet:</strong> {row['diet']}<br>"
            f"<strong>Length (m):</strong> {row['length_m']}<br>"
            f"<strong>Age (Ma):</strong> {row['mid_ma']}<br>"
            f"<strong>Region:</strong> {row['region']}<br>"
            f"<strong>Family:</strong> {row['family']}<br>"
        )
    ).add_to(marker_cluster)

# Display the map
m