EDA awal

Memenangi Kompetisi Kaggle dengan Python

Yauhen Babakhin

Kaggle Grandmaster

Tujuan EDA

Ukuran data
Sifat variabel target
Sifat fitur
Ide rekayasa fitur

Two Sigma Connect: permintaan info listing sewa

Rumusan masalah
Prediksi popularitas listing sewa apartemen

Variabel target
interest_level

Tipe masalah
Klasifikasi 3 kelas: 'high', 'medium', 'low'

Metrik
Multi-class logarithmic loss

EDA. Bagian I

# Ukuran data
twosigma_train = pd.read_csv('twosigma_train.csv')
print('Train shape:', twosigma_train.shape)

twosigma_test = pd.read_csv('twosigma_test.csv')
print('Test shape:', twosigma_test.shape)

Train shape: (49352, 11)
Test shape: (74659, 10)

EDA. Bagian I

print(twosigma_train.columns.tolist())

['id', 'bathrooms', 'bedrooms', 'building_id', 'latitude', 'longitude',
'manager_id', 'price', 'interest_level']

twosigma_train.interest_level.value_counts()

low       34284
medium    11229
high       3839

EDA. Bagian I

# Deskripsikan data train
twosigma_train.describe()

         bathrooms      bedrooms      latitude     longitude         price
count  49352.00000  49352.000000  49352.000000  49352.000000  4.935200e+04
mean       1.21218      1.541640     40.741545    -73.955716  3.830174e+03
std        0.50142      1.115018      0.638535      1.177912  2.206687e+04
min        0.00000      0.000000      0.000000   -118.271000  4.300000e+01
25%        1.00000      1.000000     40.728300    -73.991700  2.500000e+03
50%        1.00000      1.000000     40.751800    -73.977900  3.150000e+03
75%        1.00000      2.000000     40.774300    -73.954800  4.100000e+03
max       10.00000      8.000000     44.883500      0.000000  4.490000e+06

EDA. Bagian II

import matplotlib.pyplot as plt
plt.style.use('ggplot')

# Cari median harga per tingkat minat
prices = twosigma_train.groupby('interest_level', as_index=False)['price'].median()

EDA. Bagian II

# Gambar barplot
fig = plt.figure(figsize=(7, 5))
plt.bar(prices.interest_level, prices.price, width=0.5, alpha=0.8)

# Atur judul/sumbu
plt.xlabel('Interest level')
plt.ylabel('Median price')
plt.title('Median listing price across interest level')

# Tampilkan plot
plt.show()

median harga listing menurut tingkat minat

Ayo berlatih!

Memenangi Kompetisi Kaggle dengan Python