Clustering is a popular and elegant unsupervised learning technique which helps find patterns in the underlying data. Clustering does not use any Y variables or labels on the data. It looks at the data structure itself.
import pandas as pd
Download link: https://www.kaggle.com/c/3136/download/train.csv
Summary: Information about passengers who were on the Titanic including whether they survived
titanic_data = pd.read_csv('../data/titanic.csv', quotechar='"')
titanic_data.head()
PassengerId | Survived | Pclass | Name | Sex | Age | SibSp | Parch | Ticket | Fare | Cabin | Embarked | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0 | 3 | Braund, Mr. Owen Harris | male | 22.0 | 1 | 0 | A/5 21171 | 7.2500 | NaN | S |
1 | 2 | 1 | 1 | Cumings, Mrs. John Bradley (Florence Briggs Th... | female | 38.0 | 1 | 0 | PC 17599 | 71.2833 | C85 | C |
2 | 3 | 1 | 3 | Heikkinen, Miss. Laina | female | 26.0 | 0 | 0 | STON/O2. 3101282 | 7.9250 | NaN | S |
3 | 4 | 1 | 1 | Futrelle, Mrs. Jacques Heath (Lily May Peel) | female | 35.0 | 1 | 0 | 113803 | 53.1000 | C123 | S |
4 | 5 | 0 | 3 | Allen, Mr. William Henry | male | 35.0 | 0 | 0 | 373450 | 8.0500 | NaN | S |
titanic_data.drop(['PassengerId', 'Name', 'Ticket', 'Cabin'], 'columns', inplace=True)
titanic_data.head()
Survived | Pclass | Sex | Age | SibSp | Parch | Fare | Embarked | |
---|---|---|---|---|---|---|---|---|
0 | 0 | 3 | male | 22.0 | 1 | 0 | 7.2500 | S |
1 | 1 | 1 | female | 38.0 | 1 | 0 | 71.2833 | C |
2 | 1 | 3 | female | 26.0 | 0 | 0 | 7.9250 | S |
3 | 1 | 1 | female | 35.0 | 1 | 0 | 53.1000 | S |
4 | 0 | 3 | male | 35.0 | 0 | 0 | 8.0500 | S |
from sklearn import preprocessing
le = preprocessing.LabelEncoder()
titanic_data['Sex'] = le.fit_transform(titanic_data['Sex'].astype(str))
titanic_data.head()
Survived | Pclass | Sex | Age | SibSp | Parch | Fare | Embarked | |
---|---|---|---|---|---|---|---|---|
0 | 0 | 3 | 1 | 22.0 | 1 | 0 | 7.2500 | S |
1 | 1 | 1 | 0 | 38.0 | 1 | 0 | 71.2833 | C |
2 | 1 | 3 | 0 | 26.0 | 0 | 0 | 7.9250 | S |
3 | 1 | 1 | 0 | 35.0 | 1 | 0 | 53.1000 | S |
4 | 0 | 3 | 1 | 35.0 | 0 | 0 | 8.0500 | S |
titanic_data = pd.get_dummies(titanic_data, columns=['Embarked'])
titanic_data.head()
Survived | Pclass | Sex | Age | SibSp | Parch | Fare | Embarked_C | Embarked_Q | Embarked_S | |
---|---|---|---|---|---|---|---|---|---|---|
0 | 0 | 3 | 1 | 22.0 | 1 | 0 | 7.2500 | 0 | 0 | 1 |
1 | 1 | 1 | 0 | 38.0 | 1 | 0 | 71.2833 | 1 | 0 | 0 |
2 | 1 | 3 | 0 | 26.0 | 0 | 0 | 7.9250 | 0 | 0 | 1 |
3 | 1 | 1 | 0 | 35.0 | 1 | 0 | 53.1000 | 0 | 0 | 1 |
4 | 0 | 3 | 1 | 35.0 | 0 | 0 | 8.0500 | 0 | 0 | 1 |
titanic_data[titanic_data.isnull().any(axis=1)]
Survived | Pclass | Sex | Age | SibSp | Parch | Fare | Embarked_C | Embarked_Q | Embarked_S | |
---|---|---|---|---|---|---|---|---|---|---|
5 | 0 | 3 | 1 | NaN | 0 | 0 | 8.4583 | 0 | 1 | 0 |
17 | 1 | 2 | 1 | NaN | 0 | 0 | 13.0000 | 0 | 0 | 1 |
19 | 1 | 3 | 0 | NaN | 0 | 0 | 7.2250 | 1 | 0 | 0 |
26 | 0 | 3 | 1 | NaN | 0 | 0 | 7.2250 | 1 | 0 | 0 |
28 | 1 | 3 | 0 | NaN | 0 | 0 | 7.8792 | 0 | 1 | 0 |
29 | 0 | 3 | 1 | NaN | 0 | 0 | 7.8958 | 0 | 0 | 1 |
31 | 1 | 1 | 0 | NaN | 1 | 0 | 146.5208 | 1 | 0 | 0 |
32 | 1 | 3 | 0 | NaN | 0 | 0 | 7.7500 | 0 | 1 | 0 |
36 | 1 | 3 | 1 | NaN | 0 | 0 | 7.2292 | 1 | 0 | 0 |
42 | 0 | 3 | 1 | NaN | 0 | 0 | 7.8958 | 1 | 0 | 0 |
45 | 0 | 3 | 1 | NaN | 0 | 0 | 8.0500 | 0 | 0 | 1 |
46 | 0 | 3 | 1 | NaN | 1 | 0 | 15.5000 | 0 | 1 | 0 |
47 | 1 | 3 | 0 | NaN | 0 | 0 | 7.7500 | 0 | 1 | 0 |
48 | 0 | 3 | 1 | NaN | 2 | 0 | 21.6792 | 1 | 0 | 0 |
55 | 1 | 1 | 1 | NaN | 0 | 0 | 35.5000 | 0 | 0 | 1 |
64 | 0 | 1 | 1 | NaN | 0 | 0 | 27.7208 | 1 | 0 | 0 |
65 | 1 | 3 | 1 | NaN | 1 | 1 | 15.2458 | 1 | 0 | 0 |
76 | 0 | 3 | 1 | NaN | 0 | 0 | 7.8958 | 0 | 0 | 1 |
77 | 0 | 3 | 1 | NaN | 0 | 0 | 8.0500 | 0 | 0 | 1 |
82 | 1 | 3 | 0 | NaN | 0 | 0 | 7.7875 | 0 | 1 | 0 |
87 | 0 | 3 | 1 | NaN | 0 | 0 | 8.0500 | 0 | 0 | 1 |
95 | 0 | 3 | 1 | NaN | 0 | 0 | 8.0500 | 0 | 0 | 1 |
101 | 0 | 3 | 1 | NaN | 0 | 0 | 7.8958 | 0 | 0 | 1 |
107 | 1 | 3 | 1 | NaN | 0 | 0 | 7.7750 | 0 | 0 | 1 |
109 | 1 | 3 | 0 | NaN | 1 | 0 | 24.1500 | 0 | 1 | 0 |
121 | 0 | 3 | 1 | NaN | 0 | 0 | 8.0500 | 0 | 0 | 1 |
126 | 0 | 3 | 1 | NaN | 0 | 0 | 7.7500 | 0 | 1 | 0 |
128 | 1 | 3 | 0 | NaN | 1 | 1 | 22.3583 | 1 | 0 | 0 |
140 | 0 | 3 | 0 | NaN | 0 | 2 | 15.2458 | 1 | 0 | 0 |
154 | 0 | 3 | 1 | NaN | 0 | 0 | 7.3125 | 0 | 0 | 1 |
... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
718 | 0 | 3 | 1 | NaN | 0 | 0 | 15.5000 | 0 | 1 | 0 |
727 | 1 | 3 | 0 | NaN | 0 | 0 | 7.7375 | 0 | 1 | 0 |
732 | 0 | 2 | 1 | NaN | 0 | 0 | 0.0000 | 0 | 0 | 1 |
738 | 0 | 3 | 1 | NaN | 0 | 0 | 7.8958 | 0 | 0 | 1 |
739 | 0 | 3 | 1 | NaN | 0 | 0 | 7.8958 | 0 | 0 | 1 |
740 | 1 | 1 | 1 | NaN | 0 | 0 | 30.0000 | 0 | 0 | 1 |
760 | 0 | 3 | 1 | NaN | 0 | 0 | 14.5000 | 0 | 0 | 1 |
766 | 0 | 1 | 1 | NaN | 0 | 0 | 39.6000 | 1 | 0 | 0 |
768 | 0 | 3 | 1 | NaN | 1 | 0 | 24.1500 | 0 | 1 | 0 |
773 | 0 | 3 | 1 | NaN | 0 | 0 | 7.2250 | 1 | 0 | 0 |
776 | 0 | 3 | 1 | NaN | 0 | 0 | 7.7500 | 0 | 1 | 0 |
778 | 0 | 3 | 1 | NaN | 0 | 0 | 7.7375 | 0 | 1 | 0 |
783 | 0 | 3 | 1 | NaN | 1 | 2 | 23.4500 | 0 | 0 | 1 |
790 | 0 | 3 | 1 | NaN | 0 | 0 | 7.7500 | 0 | 1 | 0 |
792 | 0 | 3 | 0 | NaN | 8 | 2 | 69.5500 | 0 | 0 | 1 |
793 | 0 | 1 | 1 | NaN | 0 | 0 | 30.6958 | 1 | 0 | 0 |
815 | 0 | 1 | 1 | NaN | 0 | 0 | 0.0000 | 0 | 0 | 1 |
825 | 0 | 3 | 1 | NaN | 0 | 0 | 6.9500 | 0 | 1 | 0 |
826 | 0 | 3 | 1 | NaN | 0 | 0 | 56.4958 | 0 | 0 | 1 |
828 | 1 | 3 | 1 | NaN | 0 | 0 | 7.7500 | 0 | 1 | 0 |
832 | 0 | 3 | 1 | NaN | 0 | 0 | 7.2292 | 1 | 0 | 0 |
837 | 0 | 3 | 1 | NaN | 0 | 0 | 8.0500 | 0 | 0 | 1 |
839 | 1 | 1 | 1 | NaN | 0 | 0 | 29.7000 | 1 | 0 | 0 |
846 | 0 | 3 | 1 | NaN | 8 | 2 | 69.5500 | 0 | 0 | 1 |
849 | 1 | 1 | 0 | NaN | 1 | 0 | 89.1042 | 1 | 0 | 0 |
859 | 0 | 3 | 1 | NaN | 0 | 0 | 7.2292 | 1 | 0 | 0 |
863 | 0 | 3 | 0 | NaN | 8 | 2 | 69.5500 | 0 | 0 | 1 |
868 | 0 | 3 | 1 | NaN | 0 | 0 | 9.5000 | 0 | 0 | 1 |
878 | 0 | 3 | 1 | NaN | 0 | 0 | 7.8958 | 0 | 0 | 1 |
888 | 0 | 3 | 0 | NaN | 1 | 2 | 23.4500 | 0 | 0 | 1 |
177 rows × 10 columns
titanic_data = titanic_data.dropna()
from sklearn.cluster import MeanShift
analyzer = MeanShift(bandwidth=30)
analyzer.fit(titanic_data)
MeanShift(bandwidth=30, bin_seeding=False, cluster_all=True, min_bin_freq=1, n_jobs=None, seeds=None)
# Getting the size of the bandwidth which MeanShift will have used by default
from sklearn.cluster import estimate_bandwidth
estimate_bandwidth(titanic_data)
30.44675914497196
labels = analyzer.labels_
import numpy as np
np.unique(labels)
array([0, 1, 2, 3, 4], dtype=int64)
import numpy as np
titanic_data['cluster_group'] = np.nan
data_length = len(titanic_data)
for i in range(data_length):
titanic_data.iloc[i, titanic_data.columns.get_loc('cluster_group')] = labels[i]
titanic_data.head()
Survived | Pclass | Sex | Age | SibSp | Parch | Fare | Embarked_C | Embarked_Q | Embarked_S | cluster_group | |
---|---|---|---|---|---|---|---|---|---|---|---|
0 | 0 | 3 | 1 | 22.0 | 1 | 0 | 7.2500 | 0 | 0 | 1 | 0.0 |
1 | 1 | 1 | 0 | 38.0 | 1 | 0 | 71.2833 | 1 | 0 | 0 | 1.0 |
2 | 1 | 3 | 0 | 26.0 | 0 | 0 | 7.9250 | 0 | 0 | 1 | 0.0 |
3 | 1 | 1 | 0 | 35.0 | 1 | 0 | 53.1000 | 0 | 0 | 1 | 1.0 |
4 | 0 | 3 | 1 | 35.0 | 0 | 0 | 8.0500 | 0 | 0 | 1 | 0.0 |
titanic_data.describe()
Survived | Pclass | Sex | Age | SibSp | Parch | Fare | Embarked_C | Embarked_Q | Embarked_S | cluster_group | |
---|---|---|---|---|---|---|---|---|---|---|---|
count | 714.000000 | 714.000000 | 714.000000 | 714.000000 | 714.000000 | 714.000000 | 714.000000 | 714.000000 | 714.000000 | 714.000000 | 714.000000 |
mean | 0.406162 | 2.236695 | 0.634454 | 29.699118 | 0.512605 | 0.431373 | 34.694514 | 0.182073 | 0.039216 | 0.775910 | 0.315126 |
std | 0.491460 | 0.838250 | 0.481921 | 14.526497 | 0.929783 | 0.853289 | 52.918930 | 0.386175 | 0.194244 | 0.417274 | 0.690647 |
min | 0.000000 | 1.000000 | 0.000000 | 0.420000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 |
25% | 0.000000 | 1.000000 | 0.000000 | 20.125000 | 0.000000 | 0.000000 | 8.050000 | 0.000000 | 0.000000 | 1.000000 | 0.000000 |
50% | 0.000000 | 2.000000 | 1.000000 | 28.000000 | 0.000000 | 0.000000 | 15.741700 | 0.000000 | 0.000000 | 1.000000 | 0.000000 |
75% | 1.000000 | 3.000000 | 1.000000 | 38.000000 | 1.000000 | 1.000000 | 33.375000 | 0.000000 | 0.000000 | 1.000000 | 0.000000 |
max | 1.000000 | 3.000000 | 1.000000 | 80.000000 | 5.000000 | 6.000000 | 512.329200 | 1.000000 | 1.000000 | 1.000000 | 4.000000 |
titanic_cluster_data = titanic_data.groupby(['cluster_group']).mean()
titanic_cluster_data
Survived | Pclass | Sex | Age | SibSp | Parch | Fare | Embarked_C | Embarked_Q | Embarked_S | |
---|---|---|---|---|---|---|---|---|---|---|
cluster_group | ||||||||||
0.0 | 0.336918 | 2.525090 | 0.679211 | 28.256720 | 0.439068 | 0.370968 | 15.434139 | 0.121864 | 0.046595 | 0.831541 |
1.0 | 0.611111 | 1.296296 | 0.527778 | 36.148148 | 0.814815 | 0.500000 | 65.622688 | 0.333333 | 0.018519 | 0.629630 |
2.0 | 0.733333 | 1.000000 | 0.366667 | 32.430667 | 0.600000 | 0.866667 | 131.183883 | 0.500000 | 0.000000 | 0.500000 |
3.0 | 0.733333 | 1.000000 | 0.266667 | 30.333333 | 1.000000 | 1.333333 | 239.991940 | 0.533333 | 0.000000 | 0.466667 |
4.0 | 1.000000 | 1.000000 | 0.666667 | 35.333333 | 0.000000 | 0.333333 | 512.329200 | 1.000000 | 0.000000 | 0.000000 |
titanic_cluster_data['Counts'] = pd.Series(titanic_data.groupby(['cluster_group']).size())
titanic_cluster_data
Survived | Pclass | Sex | Age | SibSp | Parch | Fare | Embarked_C | Embarked_Q | Embarked_S | Counts | |
---|---|---|---|---|---|---|---|---|---|---|---|
cluster_group | |||||||||||
0.0 | 0.336918 | 2.525090 | 0.679211 | 28.256720 | 0.439068 | 0.370968 | 15.434139 | 0.121864 | 0.046595 | 0.831541 | 558 |
1.0 | 0.611111 | 1.296296 | 0.527778 | 36.148148 | 0.814815 | 0.500000 | 65.622688 | 0.333333 | 0.018519 | 0.629630 | 108 |
2.0 | 0.733333 | 1.000000 | 0.366667 | 32.430667 | 0.600000 | 0.866667 | 131.183883 | 0.500000 | 0.000000 | 0.500000 | 30 |
3.0 | 0.733333 | 1.000000 | 0.266667 | 30.333333 | 1.000000 | 1.333333 | 239.991940 | 0.533333 | 0.000000 | 0.466667 | 15 |
4.0 | 1.000000 | 1.000000 | 0.666667 | 35.333333 | 0.000000 | 0.333333 | 512.329200 | 1.000000 | 0.000000 | 0.000000 | 3 |
titanic_data[ titanic_data['cluster_group'] == 1 ].describe()
Survived | Pclass | Sex | Age | SibSp | Parch | Fare | Embarked_C | Embarked_Q | Embarked_S | cluster_group | |
---|---|---|---|---|---|---|---|---|---|---|---|
count | 108.000000 | 108.000000 | 108.000000 | 108.000000 | 108.000000 | 108.000000 | 108.000000 | 108.000000 | 108.000000 | 108.000000 | 108.0 |
mean | 0.611111 | 1.296296 | 0.527778 | 36.148148 | 0.814815 | 0.500000 | 65.622688 | 0.333333 | 0.018519 | 0.629630 | 1.0 |
std | 0.489771 | 0.645028 | 0.501555 | 14.919607 | 1.086434 | 0.971558 | 15.634315 | 0.473602 | 0.135445 | 0.485155 | 0.0 |
min | 0.000000 | 1.000000 | 0.000000 | 1.000000 | 0.000000 | 0.000000 | 34.654200 | 0.000000 | 0.000000 | 0.000000 | 1.0 |
25% | 0.000000 | 1.000000 | 0.000000 | 24.000000 | 0.000000 | 0.000000 | 52.554200 | 0.000000 | 0.000000 | 0.000000 | 1.0 |
50% | 1.000000 | 1.000000 | 1.000000 | 35.000000 | 1.000000 | 0.000000 | 65.000000 | 0.000000 | 0.000000 | 1.000000 | 1.0 |
75% | 1.000000 | 1.000000 | 1.000000 | 48.000000 | 1.000000 | 1.000000 | 78.937500 | 1.000000 | 0.000000 | 1.000000 | 1.0 |
max | 1.000000 | 3.000000 | 1.000000 | 71.000000 | 5.000000 | 6.000000 | 93.500000 | 1.000000 | 1.000000 | 1.000000 | 1.0 |
titanic_data[ titanic_data['cluster_group'] == 0]
Survived | Pclass | Sex | Age | SibSp | Parch | Fare | Embarked_C | Embarked_Q | Embarked_S | cluster_group | |
---|---|---|---|---|---|---|---|---|---|---|---|
0 | 0 | 3 | 1 | 22.0 | 1 | 0 | 7.2500 | 0 | 0 | 1 | 0.0 |
2 | 1 | 3 | 0 | 26.0 | 0 | 0 | 7.9250 | 0 | 0 | 1 | 0.0 |
4 | 0 | 3 | 1 | 35.0 | 0 | 0 | 8.0500 | 0 | 0 | 1 | 0.0 |
7 | 0 | 3 | 1 | 2.0 | 3 | 1 | 21.0750 | 0 | 0 | 1 | 0.0 |
8 | 1 | 3 | 0 | 27.0 | 0 | 2 | 11.1333 | 0 | 0 | 1 | 0.0 |
9 | 1 | 2 | 0 | 14.0 | 1 | 0 | 30.0708 | 1 | 0 | 0 | 0.0 |
10 | 1 | 3 | 0 | 4.0 | 1 | 1 | 16.7000 | 0 | 0 | 1 | 0.0 |
11 | 1 | 1 | 0 | 58.0 | 0 | 0 | 26.5500 | 0 | 0 | 1 | 0.0 |
12 | 0 | 3 | 1 | 20.0 | 0 | 0 | 8.0500 | 0 | 0 | 1 | 0.0 |
13 | 0 | 3 | 1 | 39.0 | 1 | 5 | 31.2750 | 0 | 0 | 1 | 0.0 |
14 | 0 | 3 | 0 | 14.0 | 0 | 0 | 7.8542 | 0 | 0 | 1 | 0.0 |
15 | 1 | 2 | 0 | 55.0 | 0 | 0 | 16.0000 | 0 | 0 | 1 | 0.0 |
16 | 0 | 3 | 1 | 2.0 | 4 | 1 | 29.1250 | 0 | 1 | 0 | 0.0 |
18 | 0 | 3 | 0 | 31.0 | 1 | 0 | 18.0000 | 0 | 0 | 1 | 0.0 |
20 | 0 | 2 | 1 | 35.0 | 0 | 0 | 26.0000 | 0 | 0 | 1 | 0.0 |
21 | 1 | 2 | 1 | 34.0 | 0 | 0 | 13.0000 | 0 | 0 | 1 | 0.0 |
22 | 1 | 3 | 0 | 15.0 | 0 | 0 | 8.0292 | 0 | 1 | 0 | 0.0 |
23 | 1 | 1 | 1 | 28.0 | 0 | 0 | 35.5000 | 0 | 0 | 1 | 0.0 |
24 | 0 | 3 | 0 | 8.0 | 3 | 1 | 21.0750 | 0 | 0 | 1 | 0.0 |
25 | 1 | 3 | 0 | 38.0 | 1 | 5 | 31.3875 | 0 | 0 | 1 | 0.0 |
30 | 0 | 1 | 1 | 40.0 | 0 | 0 | 27.7208 | 1 | 0 | 0 | 0.0 |
33 | 0 | 2 | 1 | 66.0 | 0 | 0 | 10.5000 | 0 | 0 | 1 | 0.0 |
37 | 0 | 3 | 1 | 21.0 | 0 | 0 | 8.0500 | 0 | 0 | 1 | 0.0 |
38 | 0 | 3 | 0 | 18.0 | 2 | 0 | 18.0000 | 0 | 0 | 1 | 0.0 |
39 | 1 | 3 | 0 | 14.0 | 1 | 0 | 11.2417 | 1 | 0 | 0 | 0.0 |
40 | 0 | 3 | 0 | 40.0 | 1 | 0 | 9.4750 | 0 | 0 | 1 | 0.0 |
41 | 0 | 2 | 0 | 27.0 | 1 | 0 | 21.0000 | 0 | 0 | 1 | 0.0 |
43 | 1 | 2 | 0 | 3.0 | 1 | 2 | 41.5792 | 1 | 0 | 0 | 0.0 |
44 | 1 | 3 | 0 | 19.0 | 0 | 0 | 7.8792 | 0 | 1 | 0 | 0.0 |
49 | 0 | 3 | 0 | 18.0 | 1 | 0 | 17.8000 | 0 | 0 | 1 | 0.0 |
... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
852 | 0 | 3 | 0 | 9.0 | 1 | 1 | 15.2458 | 1 | 0 | 0 | 0.0 |
853 | 1 | 1 | 0 | 16.0 | 0 | 1 | 39.4000 | 0 | 0 | 1 | 0.0 |
854 | 0 | 2 | 0 | 44.0 | 1 | 0 | 26.0000 | 0 | 0 | 1 | 0.0 |
855 | 1 | 3 | 0 | 18.0 | 0 | 1 | 9.3500 | 0 | 0 | 1 | 0.0 |
857 | 1 | 1 | 1 | 51.0 | 0 | 0 | 26.5500 | 0 | 0 | 1 | 0.0 |
858 | 1 | 3 | 0 | 24.0 | 0 | 3 | 19.2583 | 1 | 0 | 0 | 0.0 |
860 | 0 | 3 | 1 | 41.0 | 2 | 0 | 14.1083 | 0 | 0 | 1 | 0.0 |
861 | 0 | 2 | 1 | 21.0 | 1 | 0 | 11.5000 | 0 | 0 | 1 | 0.0 |
862 | 1 | 1 | 0 | 48.0 | 0 | 0 | 25.9292 | 0 | 0 | 1 | 0.0 |
864 | 0 | 2 | 1 | 24.0 | 0 | 0 | 13.0000 | 0 | 0 | 1 | 0.0 |
865 | 1 | 2 | 0 | 42.0 | 0 | 0 | 13.0000 | 0 | 0 | 1 | 0.0 |
866 | 1 | 2 | 0 | 27.0 | 1 | 0 | 13.8583 | 1 | 0 | 0 | 0.0 |
869 | 1 | 3 | 1 | 4.0 | 1 | 1 | 11.1333 | 0 | 0 | 1 | 0.0 |
870 | 0 | 3 | 1 | 26.0 | 0 | 0 | 7.8958 | 0 | 0 | 1 | 0.0 |
872 | 0 | 1 | 1 | 33.0 | 0 | 0 | 5.0000 | 0 | 0 | 1 | 0.0 |
873 | 0 | 3 | 1 | 47.0 | 0 | 0 | 9.0000 | 0 | 0 | 1 | 0.0 |
874 | 1 | 2 | 0 | 28.0 | 1 | 0 | 24.0000 | 1 | 0 | 0 | 0.0 |
875 | 1 | 3 | 0 | 15.0 | 0 | 0 | 7.2250 | 1 | 0 | 0 | 0.0 |
876 | 0 | 3 | 1 | 20.0 | 0 | 0 | 9.8458 | 0 | 0 | 1 | 0.0 |
877 | 0 | 3 | 1 | 19.0 | 0 | 0 | 7.8958 | 0 | 0 | 1 | 0.0 |
880 | 1 | 2 | 0 | 25.0 | 0 | 1 | 26.0000 | 0 | 0 | 1 | 0.0 |
881 | 0 | 3 | 1 | 33.0 | 0 | 0 | 7.8958 | 0 | 0 | 1 | 0.0 |
882 | 0 | 3 | 0 | 22.0 | 0 | 0 | 10.5167 | 0 | 0 | 1 | 0.0 |
883 | 0 | 2 | 1 | 28.0 | 0 | 0 | 10.5000 | 0 | 0 | 1 | 0.0 |
884 | 0 | 3 | 1 | 25.0 | 0 | 0 | 7.0500 | 0 | 0 | 1 | 0.0 |
885 | 0 | 3 | 0 | 39.0 | 0 | 5 | 29.1250 | 0 | 1 | 0 | 0.0 |
886 | 0 | 2 | 1 | 27.0 | 0 | 0 | 13.0000 | 0 | 0 | 1 | 0.0 |
887 | 1 | 1 | 0 | 19.0 | 0 | 0 | 30.0000 | 0 | 0 | 1 | 0.0 |
889 | 1 | 1 | 1 | 26.0 | 0 | 0 | 30.0000 | 1 | 0 | 0 | 0.0 |
890 | 0 | 3 | 1 | 32.0 | 0 | 0 | 7.7500 | 0 | 1 | 0 | 0.0 |
558 rows × 11 columns