Dinosaur and Films Dataset Analysis

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

import numpy as np
import pandas as pd 
# Load the data
df = pd.read_csv('data/dinosaurs.csv')

#1. How many different dinosaur names are present in the data? 1042

unique_dinosaur_names = df['name'].dropna()
unique_dinosaur_names = df['name'].nunique()

print("Number of different dinosaur names:", unique_dinosaur_names)

#2. Which was the largest dinosaur? Supersaurus
largest_dinosaur = df.loc[df['length_m'].idxmax()]['name']
#What about missing data in the dataset? 
df.isnull().sum()

largest_dinosaur = df.loc[df['length_m'].idxmax()]

# Check for missing data in the dataset
missing_data_summary = df.isnull().sum()

print("Largest Dinosaur:")
print(largest_dinosaur)
print("\nMissing Data Summary:")
print(missing_data_summary)

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

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

# Clean the data: Drop rows with missing 'type' values
clean_df = df.dropna(subset=['type'])

# Group by 'type' and count occurrences
type_counts = clean_df['type'].value_counts()

# Create the bar plot
plt.figure(figsize=(12, 8))
sns.barplot(x=type_counts.index, y=type_counts.values, palette='viridis')

# 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)
plt.xticks(rotation=45, ha='right')
plt.grid(axis='y')

# Display the plot
plt.show()

# Save the cleaned dataframe to a new CSV file
cleaned_file_path = 'data/dinosaurs_cleaned.csv'
clean_df.to_csv(cleaned_file_path, index=False)

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
import seaborn as sns

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

# Calculate the midpoint of the age interval
df['mid_ma'] = (df['max_ma'] + df['min_ma']) / 2
df['duration'] = np.abs(df['max_ma'] - df['min_ma'])  # Duration of existence

# Drop rows with missing values in 'mid_ma' and 'max_ma'
df.dropna(subset=['mid_ma', 'max_ma','type'], inplace=True)

# Drop rows with any remaining missing values
df.dropna(inplace=True)

# Create the plot
plt.figure(figsize=(12, 8))
ax = plt.gca()

# Count the occurrences of each dinosaur type
type_counts = df['type'].value_counts()

# Create a color palette based on the unique types
unique_types = df['type'].unique()
palette = sns.color_palette("tab10", len(unique_types))
type_colors = {type_name: palette[i] for i, type_name in enumerate(unique_types)}

# Plot each data point as an ellipse
for idx, row in df.iterrows():
    ellipse = mpatches.Ellipse((row['mid_ma'], row['length_m']),
                               width=row['duration'] / 2, height=.1,  # Adjust these values to stretch the marker
                               edgecolor=type_colors[row['type']], facecolor='none')
    ax.add_patch(ellipse)

# Customize the plot
plt.xlim(df['mid_ma'].max() + 10, df['mid_ma'].min() - 10)  # Extend limits for better visualization
plt.ylim(0, max(df['length_m']) + 10)
plt.title('Dinosaur Length Over Time with Elliptical Markers')
plt.xlabel('Age Midpoint (Millions of Years Ago)')
plt.ylabel('Length (Meters)')

# Create a legend
handles = [mpatches.Patch(color=type_colors[type_name], label=type_name) for type_name in unique_types]
plt.legend(handles=handles, title="Dinosaur Type")

# Show the plot
plt.show()

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


# Set up the plot
fig, (ax1, ax2) = plt.subplots(nrows=1, ncols=2, figsize=(18, 8))

# Iterate over each dinosaur type
types = df['type'].unique()
for dinosaur_type in types:
    subset = df[df['type'] == dinosaur_type]

    # Plot the scatter points and the regression line
    sns.scatterplot(x='mid_ma', y='length_m', data=subset, label=dinosaur_type, ax=ax1)
    sns.regplot(x='mid_ma', y='length_m', data=subset, order=2, scatter=False, ax=ax1)

# Customize the scatter plot
ax1.set_title('Dinosaur Length Over Time by Type with Polynomial Regression')
ax1.set_xlabel('Midpoint Age (Millions of Years Ago)')
ax1.set_ylabel('Length (Meters)')
ax1.invert_xaxis()  # Invert the x-axis so older ages (higher values) are on the left
ax1.legend()
# Plot the KDE for all fossils
sns.kdeplot(data=df['mid_ma'], bw_adjust=1, color='blue', label='All Fossils', ax=ax2)

# Customize the KDE plot
ax2.set_title('Density Plot of All Fossils Over Time')
ax2.set_xlabel('Midpoint Age (Millions of Years Ago)')
ax2.set_ylabel('Density')
ax2.invert_xaxis()  # Invert the x-axis so older ages (higher values) are on the left
ax2.legend()

# Set the same x-axis limits for both subplots
min_x = df['mid_ma'].min()
max_x = df['mid_ma'].max()
ax1.set_xlim(max_x, min_x)
ax2.set_xlim(max_x, min_x)

plt.tight_layout()
plt.show()