Story 3¶

# Write response to pandas dataframe
df = pd.json_normalize(response)
df.head()

# Select only needed columns and transpose our data
state_cols = ['year_and_quarter', 'rate_alaska', 'rate_alabama', 'rate_arkansas', 'rate_arizona',
              'rate_california', 'rate_colorado', 'rate_connecticut',
              'rate_district_of_columbia', 'rate_delaware', 'rate_florida',
              'rate_georgia', 'rate_hawaii', 'rate_iowa', 'rate_idaho',
              'rate_illinois', 'rate_indiana', 'rate_kansas', 'rate_kentucky',
              'rate_louisiana', 'rate_massachusetts', 'rate_maryland', 'rate_maine',
              'rate_michigan', 'rate_minnesota', 'rate_missouri', 'rate_mississippi',
              'rate_montana', 'rate_north_carolina', 'rate_north_dakota',
              'rate_nebraska', 'rate_new_hampshire', 'rate_new_jersey',
              'rate_new_mexico', 'rate_nevada', 'rate_new_york', 'rate_ohio',
              'rate_oklahoma', 'rate_oregon', 'rate_pennsylvania',
              'rate_rhode_island', 'rate_south_carolina', 'rate_south_dakota',
              'rate_tennessee', 'rate_texas', 'rate_utah', 'rate_virginia',
              'rate_vermont', 'rate_washington', 'rate_wisconsin',
              'rate_west_virginia', 'rate_wyoming', 'rate_overall']
df = df[state_cols].transpose()

# Set the first row (year_and_quarter) as column headers and remove it from the data
df.columns = df.iloc[0]
df = df.drop(df.index[0])

# Clean up state names and set index
df['state'] = [s.replace("_", " ").replace("rate", "").title().strip() for s in df.index]
df = df.set_index('state')

# Convert column data to float, skipping over missing data (NaN)
for col in df.columns:
    df[col] = pd.to_numeric(df[col], errors='coerce')

# Display the cleaned DataFrame
df.head()

df_sorted = df.sort_values("2023 Q3", ascending=False)
order = df.groupby("state").sum().sort_values(['2023 Q3'], ascending=False).index

# Plot a sorted bar chart of deaths per 100k
fig, ax = plt.subplots(figsize=(10, 10))
sns.barplot(data=df, x="2023 Q3", y="state", order=order, orient="h")
ax.set_xlabel("Firearm deaths per 100k residents")
ax.set_ylabel("State")
plt.xticks(rotation=45)

plt.show()

#  firearm mortality
df_firearm_mortality = pd.read_csv('https://raw.githubusercontent.com/waheeb123/Datasets/refs/heads/main/data-table.csv')

# Check the structure of the data
df_firearm_mortality.head()

# Load the gun law scorecard data
df_gun_law = pd.read_csv('https://raw.githubusercontent.com/waheeb123/Datasets/refs/heads/main/gifford-gun-law-scorecard.csv')

# Map the grades to a 5-point Likert scale
grade_to_likert = {
    'A': 5, 'A-': 5,
    'B+': 4, 'B': 4,
    'C+': 3, 'C': 3, 'C-': 3,
    'D+': 2, 'D': 2, 'D-': 2,
    'F': 1
}

# Apply the mapping to create a Likert scale column
df_gun_law['Likert_Scale'] = df_gun_law['grade'].map(grade_to_likert)

# Preview the DataFrame
df_gun_law.head()

# Dictionary to convert state abbreviations to full state names
us_state_abbrev = {
    'AL': 'Alabama', 'AK': 'Alaska', 'AZ': 'Arizona', 'AR': 'Arkansas', 'CA': 'California',
    'CO': 'Colorado', 'CT': 'Connecticut', 'DE': 'Delaware', 'FL': 'Florida', 'GA': 'Georgia',
    'HI': 'Hawaii', 'ID': 'Idaho', 'IL': 'Illinois', 'IN': 'Indiana', 'IA': 'Iowa',
    'KS': 'Kansas', 'KY': 'Kentucky', 'LA': 'Louisiana', 'ME': 'Maine', 'MD': 'Maryland',
    'MA': 'Massachusetts', 'MI': 'Michigan', 'MN': 'Minnesota', 'MS': 'Mississippi', 'MO': 'Missouri',
    'MT': 'Montana', 'NE': 'Nebraska', 'NV': 'Nevada', 'NH': 'New Hampshire', 'NJ': 'New Jersey',
    'NM': 'New Mexico', 'NY': 'New York', 'NC': 'North Carolina', 'ND': 'North Dakota', 'OH': 'Ohio',
    'OK': 'Oklahoma', 'OR': 'Oregon', 'PA': 'Pennsylvania', 'RI': 'Rhode Island', 'SC': 'South Carolina',
    'SD': 'South Dakota', 'TN': 'Tennessee', 'TX': 'Texas', 'UT': 'Utah', 'VT': 'Vermont',
    'VA': 'Virginia', 'WA': 'Washington', 'WV': 'West Virginia', 'WI': 'Wisconsin', 'WY': 'Wyoming'
}

# Map state abbreviations to full state names
df_firearm_mortality['state_full'] = df_firearm_mortality['STATE'].map(us_state_abbrev)

# Merge using 'state_full' and 'state' in df_gun_law
df_combined = pd.merge(df_firearm_mortality, df_gun_law, left_on='state_full', right_on='state', how='inner')

# Drop the 'URL' and 'state_full' columns
df_combined = df_combined.drop(columns=['URL', 'state'])
# Preview the combined DataFrame
df_combined.head()

# Calculate the Pearson correlation coefficient
correlation, p_value = pearsonr(df_combined['Likert_Scale'], df_combined['RATE'])

print(f"Pearson correlation coefficient: {correlation}")
print(f"P-value: {p_value}")

# Create the scatterplot with the regression line
plt.figure(figsize=(10, 6))

# Scatterplot
sns.scatterplot(data=df_combined, x='Likert_Scale', y='RATE', hue='Likert_Scale', palette='coolwarm', s=100)

# Regression line showing the correlation
sns.regplot(data=df_combined, x='Likert_Scale', y='RATE', scatter=False, color='black', line_kws={"linewidth": 2})

plt.title('Relationship Between Gun Law Strictness and Firearm Mortality')
plt.xlabel('Gun Law Strictness (Likert Scale)')
plt.ylabel('Firearm Mortality Rate per 100k (2022)')
plt.grid(True)

plt.show()

import folium
import requests

# Load a GeoJSON file for state boundaries
url = 'https://raw.githubusercontent.com/PublicaMundi/MappingAPI/master/data/geojson/us-states.json'
geojson_data = requests.get(url).json()

# Create a folium map
us_map = folium.Map(location=[37.8, -96], zoom_start=4)


# Choropleth for Gun Law Strictness (Likert scale)
choropleth = folium.Choropleth(
    geo_data=geojson_data,
    name='Gun Law Strictness (Likert Scale)',
    data=df_combined,
    columns=['state_full', 'Likert_Scale'],
    key_on='feature.properties.name',
    fill_color='YlGnBu',  # Replace this with custom colors if desired
    threshold_scale=[1, 2, 3, 4, 5],  # Likert scale 1-5
    fill_opacity=0.7,
    line_opacity=0.2,
    legend_name='Gun Law Strictness (Likert Scale)',
    nan_fill_color='white',  # Color for missing values
).add_to(us_map)

# Create a dictionary to map states to strictness values (Likert scale)
strictness_dict = df_combined.set_index('state_full')['Likert_Scale'].to_dict()

# Add popups with strictness values for each state
folium.GeoJson(
    geojson_data,
    name='State Names',
    style_function=lambda feature: {
        'fillOpacity': 0,
        'color': 'transparent'
    },
    tooltip=folium.GeoJsonTooltip(
        fields=['name'],
        aliases=['State:'],
        localize=True,
        sticky=False,
        labels=True,
        style="background-color: white; color: black; font-size: 14px; font-weight: bold;"
    ),
    popup=folium.GeoJsonPopup(
        # Create a simple popup message to display the strictness value
        fields=['name'],
        aliases=['State:'],
        localize=True,
        labels=True,
        style="background-color: white; color: black; font-size: 12px;",
        # Here we use a lambda to format the popup content
        max_width=300,
        sticky=True
    )
).add_to(us_map)

# Add custom popup content using the strictness_dict for each feature
for feature in geojson_data['features']:
    state_name = feature['properties']['name']
    strictness_value = strictness_dict.get(state_name, "N/A")
    popup_content = f'Strictness Value: {strictness_value}'

    folium.Popup(popup_content).add_to(us_map)

# Add Layer Control
folium.LayerControl().add_to(us_map)

# Save the map to an HTML file
us_map.save('us_gun_law_map_interactive.html')

# Display the map in Google Colab
from google.colab import files
files.download('us_gun_law_map_interactive.html')