FilesExpand file tree

 master

/

cluster35.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

77 lines (66 loc) · 2.1 KB

 master

/

cluster35.py

Copy path

Top

File metadata and controls

• Code
• Blame

77 lines (66 loc) · 2.1 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

74

75

76

77

#https://pythonprogramming.net/static/downloads/machine-learning-data/titanic.xls

import matplotlib.pyplot as plt

from matplotlib import style

style.use('ggplot')

import numpy as np

from sklearn.cluster import KMeans

from sklearn import preprocessing

from sklearn.model_selection import cross_validate

import pandas as pd

'''

Pclass Passenger Class (1 = 1st; 2 = 2nd; 3 = 3rd)

survival Survival (0 = No; 1 = Yes)

name Name

sex Sex

age Age

sibsp Number of Siblings/Spouses Aboard

parch Number of Parents/Children Aboard

ticket Ticket Number

fare Passenger Fare (British pound)

cabin Cabin

embarked Port of Embarkation (C = Cherbourg; Q = Queenstown; S = Southampton)

boat Lifeboat

body Body Identification Number

home.dest Home/Destination

'''

df = pd.read_excel('titanic.xls')

print(df.head())

df.drop(['body','name'], 1, inplace=True)

df.convert_objects(convert_numeric=True)

df.fillna(0, inplace=True)

print(df.head())

#print(df.head())

def handle_non_numerical_data(df):

columns = df.columns.values

for column in columns:

text_digit_vals = {}

def convert_to_int(val):

return text_digit_vals[val]

if df[column].dtype != np.int64 and df[column].dtype != np.float64:

column_contents = df[column].values.tolist()

unique_elements = set(column_contents)

#print('#'*20)

#print(unique_elements)

x = 0

for unique in unique_elements:

if unique not in text_digit_vals:

text_digit_vals[unique] = x

x+=1

df[column] = list(map(convert_to_int, df[column]))

return df

df = handle_non_numerical_data(df)

#print(df.head())

#df.drop(['sex','boat'], 1, inplace=True)

X = np.array(df.drop(['survived'], 1).astype(float))

X = preprocessing.scale(X)

y = np.array(df['survived'])

clf = KMeans(n_clusters=3)

clf.fit(X)

correct = 0

for i in range(len(X)):

predict_me = np.array(X[i].astype(float))

predict_me = predict_me.reshape(-1, len(predict_me))

prediction = clf.predict(predict_me)

if prediction[0] == y[i]:

correct += 1

print(correct/len(X))