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

plt.style.use('seaborn-v0_8-darkgrid')
sns.set_palette("husl")

df = pd.read_csv('datasets/traffic_index.csv')
print(f"Shape: {df.shape[0]} rows × {df.shape[1]} columns")

Shape: 3332 rows × 4 columns

# Display first few rows
df.head(10)

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3332 entries, 0 to 3331
Data columns (total 4 columns):
 #   Column                 Non-Null Count  Dtype  
---  ------                 --------------  -----  
 0   trafficindexdate       3332 non-null   object 
 1   minimum_traffic_index  3332 non-null   int64  
 2   maximum_traffic_index  3332 non-null   int64  
 3   average_traffic_index  3332 non-null   float64
dtypes: float64(1), int64(2), object(1)
memory usage: 104.3+ KB

df.isnull().sum()

trafficindexdate         0
minimum_traffic_index    0
maximum_traffic_index    0
average_traffic_index    0
dtype: int64

df['trafficindexdate'] = pd.to_datetime(df['trafficindexdate'], format='mixed')
df['year'] = df['trafficindexdate'].dt.year
df['month'] = df['trafficindexdate'].dt.month
df['dayofweek'] = df['trafficindexdate'].dt.dayofweek
df['dayname'] = df['trafficindexdate'].dt.day_name()
df['is_weekend'] = df['dayofweek'].isin([5, 6]).astype(int)

df[['minimum_traffic_index', 'maximum_traffic_index', 'average_traffic_index']].describe()

yearly_avg = df.groupby('year')['average_traffic_index'].agg(['mean', 'std', 'min', 'max', 'count'])
yearly_avg.columns = ['Mean', 'Std', 'Min', 'Max', 'Days']
yearly_avg

plt.figure(figsize=(15, 6))
plt.plot(df['trafficindexdate'], df['average_traffic_index'], linewidth=0.8, alpha=0.7)
plt.title('İstanbul Traffic Index Over Time', fontsize=14)
plt.xlabel('Date')
plt.ylabel('Average Traffic Index')
plt.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()

plt.figure(figsize=(14, 6))
df.boxplot(column='average_traffic_index', by='year', figsize=(14, 6))
plt.suptitle('')
plt.title('Traffic Index Distribution by Year', fontsize=14)
plt.xlabel('Year')
plt.ylabel('Average Traffic Index')
plt.tight_layout()
plt.show()

<Figure size 1400x600 with 0 Axes>

plt.figure(figsize=(12, 6))
day_order = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
day_avg = df.groupby('dayname')['average_traffic_index'].mean().reindex(day_order)
colors = ['#4ecdc4' if day not in ['Saturday', 'Sunday'] else '#ff6b6b' for day in day_order]
plt.bar(range(len(day_avg)), day_avg.values, color=colors)
plt.xticks(range(len(day_avg)), day_order, rotation=45)
plt.title('Average Traffic by Day of Week', fontsize=14)
plt.ylabel('Average Traffic Index')
plt.grid(True, alpha=0.3, axis='y')
plt.tight_layout()
plt.show()

pivot_table = df.pivot_table(
    values='average_traffic_index',
    index='month',
    columns='year',
    aggfunc='mean'
)
plt.figure(figsize=(14, 8))
sns.heatmap(pivot_table, annot=True, fmt='.1f', cmap='YlOrRd')
plt.title('Monthly Traffic Index by Year', fontsize=14)
plt.xlabel('Year')
plt.ylabel('Month')
plt.tight_layout()
plt.show()

fig, axes = plt.subplots(1, 2, figsize=(14, 5))

weekend_data = df[df['is_weekend'] == 1]['average_traffic_index']
weekday_data = df[df['is_weekend'] == 0]['average_traffic_index']

axes[0].hist(weekday_data, bins=30, alpha=0.7, label='Weekday')
axes[0].hist(weekend_data, bins=30, alpha=0.7, label='Weekend')
axes[0].set_title('Weekday vs Weekend Distribution')
axes[0].set_xlabel('Average Traffic Index')
axes[0].legend()
axes[0].grid(True, alpha=0.3)

df.boxplot(column='average_traffic_index', by='is_weekend', ax=axes[1])
axes[1].set_title('Weekday vs Weekend Comparison')
axes[1].set_xlabel('0=Weekday, 1=Weekend')
plt.suptitle('')
plt.tight_layout()
plt.show()

	trafficindexdate	minimum_traffic_index	maximum_traffic_index	average_traffic_index
0	2015-08-06 00:00:00 +0000 +0000	24	63	57.858116
1	2015-08-07 00:00:00 +0000 +0000	2	49	23.770492
2	2015-08-11 00:00:00 +0000 +0000	11	62	38.601266
3	2015-08-12 00:00:00 +0000 +0000	1	63	29.715278
4	2015-08-13 00:00:00 +0000 +0000	2	56	28.557491
5	2015-08-14 00:00:00 +0000 +0000	2	69	32.300000
6	2015-08-15 00:00:00 +0000 +0000	1	47	24.184028
7	2015-08-16 00:00:00 +0000 +0000	1	29	10.590278
8	2015-08-17 00:00:00 +0000 +0000	1	58	25.745645
9	2015-08-18 00:00:00 +0000 +0000	1	65	31.427083

	minimum_traffic_index	maximum_traffic_index	average_traffic_index
count	3332.000000	3332.000000	3332.000000
mean	2.075630	59.956483	27.830846
std	2.751651	15.613316	8.252579
min	1.000000	4.000000	1.083916
25%	1.000000	53.000000	23.651568
50%	1.000000	63.000000	28.979524
75%	2.000000	71.000000	33.491313
max	58.000000	90.000000	59.428571

	Mean	Std	Min	Max	Days
year
2015	30.475363	8.081503	7.731707	57.858116	145
2016	30.311479	8.615723	4.680556	59.428571	349
2017	25.076298	5.705280	5.153846	43.804196	356
2018	24.680702	5.927610	4.344948	40.487633	365
2019	25.681933	6.387881	4.699301	49.461538	364
2020	24.094842	9.425063	2.635688	44.482639	366
2021	28.452302	11.069990	1.083916	46.298246	365
2022	29.234242	6.723550	8.383275	44.911111	365
2023	31.241237	7.123850	4.651568	58.187500	365
2024	31.416273	7.268290	2.233333	48.375000	292

Data Science - Week 1: Introduction Assignment¶

1. Dataset Selection¶

İstanbul Trafik Endeksi (Istanbul Traffic Index)¶

2. Data Exploration¶

2.1 Basic Information¶

2.2 Preprocessing¶

2.3 Statistics¶

3. Visualizations¶

4. Findings¶