### Load Data
df = pd.read_csv('border_crossing_entry_data.csv')

# Display basic information and first few rows
print("DataFrame Info:")
df.info()
print("\nFirst 5 rows of the DataFrame:")
display(df.head())

# Data Preprocessing
# Convert 'Date' column to datetime objects. Using errors='coerce' to handle any parsing issues gracefully.
df['Date'] = pd.to_datetime(df['Date'], format='%b %Y', errors='coerce')

# Drop rows where 'Date' conversion failed (if any)
df.dropna(subset=['Date'], inplace=True)

# Extract Month and Year for easier analysis
df['Month_Num'] = df['Date'].dt.month
df['Year'] = df['Date'].dt.year

print("\nDataFrame after Date conversion and feature extraction (first 5 rows):")
display(df.head())

border_measure_traffic = df.groupby(['Border', 'Measure'])['Value'].sum().unstack(fill_value=0)

plt.figure(figsize=(14, 8))
border_measure_traffic.plot(kind='bar', figsize=(14, 8), width=0.8)
plt.title('Total Traffic Volume by Border and Measure (Jan-Apr 2024)')
plt.xlabel('Border')
plt.ylabel('Total Value')
plt.xticks(rotation=0)
plt.legend(title='Measure', bbox_to_anchor=(1.05, 1), loc='upper left')
plt.tight_layout()
plt.show()

print("\nTotal traffic by Border and Measure (sum of values):")
display(border_measure_traffic)

top_ports = df.groupby('Port Name')['Value'].sum().nlargest(10)

plt.figure(figsize=(12, 7))
sns.barplot(x=top_ports.index, y=top_ports.values, palette='viridis')
plt.title('Top 10 Busiest Ports by Total Traffic Volume (Jan-Apr 2024)')
plt.xlabel('Port Name')
plt.ylabel('Total Value')
plt.xticks(rotation=45, ha='right')
plt.tight_layout()
plt.show()

print("\nTop 10 Busiest Ports:")
display(top_ports)

monthly_trends = df.groupby(['Date', 'Measure'])['Value'].sum().unstack(fill_value=0)
# Filter for the specific measures of interest
measures_to_plot = ['Personal Vehicle Passengers', 'Trucks', 'Pedestrians']
filtered_monthly_trends = monthly_trends[measures_to_plot] if all(m in monthly_trends.columns for m in measures_to_plot) else monthly_trends.filter(items=measures_to_plot)

plt.figure(figsize=(15, 8))
sns.lineplot(data=filtered_monthly_trends)
plt.title('Monthly Traffic Trends for Key Measures (Jan-Apr 2024)')
plt.xlabel('Date')
plt.ylabel('Total Value')
plt.xticks(rotation=45)
plt.grid(True, linestyle='--', alpha=0.7)
plt.legend(title='Measure')
plt.tight_layout()
plt.show()

print("\nMonthly trends for key measures:")
display(filtered_monthly_trends)

plt.figure(figsize=(15, 8))
sns.boxplot(x='Measure', y='Value', data=df, palette='pastel')
plt.title('Distribution of Values Across Different Measures')
plt.xlabel('Measure Type')
plt.ylabel('Value')
plt.xticks(rotation=45, ha='right')
plt.yscale('log') # Use log scale due to wide range of values
plt.tight_layout()
plt.show()

print("\nDescriptive statistics for each measure:")
display(df.groupby('Measure')['Value'].describe())

print("**Anomaly 1: Extremely Low Bus Passenger Count at San Luis, Arizona**")
san_luis_buses = df[(df['Port Name'] == 'San Luis') & (df['State'] == 'Arizona') & (df['Measure'].isin(['Bus Passengers', 'Buses']))]
print("San Luis, Arizona Bus/Bus Passenger data:")
display(san_luis_buses)
print("\nInsight: The values for bus traffic at San Luis, Arizona are remarkably low compared to other measures at the same high-volume border crossing, suggesting a specific operational characteristic (e.g., bus traffic is primarily handled at a different nearby port) or a potential data entry anomaly.")

print("\n**Anomaly 2: Isolated Data Point for Progreso, Texas (Oct 2023)**")
progreso_oct_2023 = df[(df['Port Name'] == 'Progreso') & (df['State'] == 'Texas') & (df['Date'] == pd.to_datetime('Oct 2023', format='%b %Y'))]
print("Progreso, Texas, Oct 2023 data:")
display(progreso_oct_2023)
print("\nInsight: This single data point from October 2023 is isolated from the main Jan-Apr 2024 dataset, making it an outlier in terms of temporal continuity and limiting its use for trend analysis within the primary period.")

print("\n**Anomaly 3: Consistently Very Low Traffic at Smaller Ports for Specific Measures**")
low_traffic_examples = df[(df['Value'] <= 5) & (df['Measure'].isin(['Pedestrians', 'Buses', 'Trucks']))].sort_values(by='Value')
print("Examples of very low traffic entries (Value <= 5 for Pedestrians, Buses, Trucks, showing top 10):")
display(low_traffic_examples.head(10))
print("\nInsight: Several small US-Canada border crossings consistently show extremely low traffic volumes for certain measures, indicating minimal activity rather than unexpected deviations. These are not necessarily errors but highlight the vast difference in activity levels across ports.")

print("**Limited Applicability for Robust Prediction:**")
print("The dataset provides only four consecutive months of data (Jan-Apr 2024) and one isolated data point from Oct 2023. This limited time-series information is insufficient for robust statistical predictive modeling (e.g., ARIMA, Prophet) which typically requires longer historical patterns and more data points to establish reliable trends, seasonality, and confidence intervals.")

print("\n**Inferred Short-Term Trends (Qualitative):**")
print("**Increasing Traffic:** Based on the observed Jan-Apr 2024 data, major commercial truck crossings (e.g., Laredo, TX - Trucks; Blaine, WA - Trucks; Port Huron, MI - Truck Containers Loaded) show a consistent upward trend, suggesting a likelihood of continued growth in the immediate future. Similarly, personal vehicle traffic at some key US-Canada crossings (e.g., Blaine, WA - Personal Vehicles) also indicates an upward trend.")
print("**Stable or Fluctuating Traffic:** Personal vehicle and passenger traffic at some high-volume US-Mexico border crossings (e.g., San Ysidro, CA - Personal Vehicles; Ysleta, TX - Personal Vehicle Passengers) appears to be relatively stable or showing minor fluctuations within a high range, suggesting similar patterns for the next month.")
print("**Low Volume Persistence:** Ports and measures with consistently very low values (e.g., Pedestrians at many US-Canada crossings, Buses at smaller ports) are likely to maintain low volumes in the near term.")