File size: 2,545 Bytes
c2601b9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
# Importing necessary libraries
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
# Setting up seaborn
sns.set(color_codes=True)
# Function to load and preprocess data
def load_and_preprocess_data(filepath):
try:
df = pd.read_csv(filepath)
df['Start_Time'] = pd.to_datetime(df['Start_Time'], format='mixed', errors='coerce')
return df
except Exception as e:
print(f"An error occurred while loading data: {e}")
return None
# Function for plotting hourly accidents distribution
def plot_hourly_accidents(df):
try:
fig, axes = plt.subplots(4, 2, figsize=(18, 10))
plt.subplots_adjust(hspace=0.5)
blue_palette = sns.light_palette("blue", n_colors=8, reverse=True)
for i in range(8):
ax = axes[i//2, i%2]
if i == 0:
sns.histplot(df['Start_Time'].dt.hour, bins=24, ax=ax, color=blue_palette[i])
ax.set_title("Overall Hourly Accident Distribution")
else:
day_data = df[df['Start_Time'].dt.dayofweek == i-1]
sns.histplot(day_data['Start_Time'].dt.hour, bins=24, ax=ax, color=blue_palette[i])
ax.set_title(f"Hourly Distribution: {day_data['Start_Time'].dt.day_name().iloc[0]}")
ax.set_xlabel("Hour")
ax.set_ylabel("Accidents")
plt.tight_layout()
plt.show()
except Exception as e:
print(f"An error occurred while plotting hourly accidents: {e}")
# Function for plotting weather conditions
def plot_weather_conditions(df):
try:
weather = df['Weather_Condition'].value_counts().head(15)
plt.figure(figsize=(30, 10))
sns.barplot(x=weather.index, y=weather.values, palette="Reds_r")
plt.xticks(rotation=45, fontsize=15)
plt.yticks(fontsize=15)
plt.xlabel("Weather Condition", fontsize=20)
plt.ylabel("Count", fontsize=20)
plt.title("Weather Condition vs Accidents", fontsize=30)
plt.show()
except Exception as e:
print(f"An error occurred while plotting weather conditions: {e}")
# Main script
def main():
# Load and preprocess data
df = load_and_preprocess_data('US_Accidents_March23.csv')
# Check if DataFrame is loaded correctly
if df is not None and not df.empty:
# Plotting functions
plot_hourly_accidents(df)
plot_weather_conditions(df)
else:
print("Data loading failed or the DataFrame is empty.")
# Run the main script
main()
|