Misalkan ini contoh datalatih:
| No | Age | Sex | Job | Housing | Saving accounts | Checking account | Credit amount | Duration | Purpose | Risk |
| 0 | 67 | male | 2 | own | NA | little | 1169 | 6 | radio/TV | good |
| 1 | 22 | female | 2 | own | little | moderate | 5951 | 48 | radio/TV | bad |
| 2 | 49 | male | 1 | own | little | NA | 2096 | 12 | education | good |
| 3 | 45 | male | 2 | free | little | little | 7882 | 42 | furniture/equipment | good |
| 4 | 53 | male | 2 | free | little | little | 4870 | 24 | car | bad |
| 5 | 35 | male | 1 | free | NA | NA | 9055 | 36 | education | good |
| 6 | 53 | male | 2 | own | quite rich | NA | 2835 | 24 | furniture/equipment | good |
| 7 | 35 | male | 3 | rent | little | moderate | 6948 | 36 | car | good |
| 8 | 61 | male | 1 | own | rich | NA | 3059 | 12 | radio/TV | good |
| 9 | 28 | male | 3 | own | little | moderate | 5234 | 30 | car | bad |
| 10 | 25 | female | 2 | rent | little | moderate | 1295 | 12 | car | bad |
| 11 | 24 | female | 2 | rent | little | little | 4308 | 48 | business | bad |
| 12 | 22 | female | 2 | own | little | moderate | 1567 | 12 | radio/TV | good |
| 13 | 60 | male | 1 | own | little | little | 1199 | 24 | car | bad |
| 14 | 28 | female | 2 | rent | little | little | 1403 | 15 | car | good |
| 15 | 32 | female | 1 | own | moderate | little | 1282 | 24 | radio/TV | bad |
| 16 | 53 | male | 2 | own | NA | NA | 2424 | 24 | radio/TV | good |
| 17 | 25 | male | 2 | own | NA | little | 8072 | 30 | business | good |
| 18 | 44 | female | 3 | free | little | moderate | 12579 | 24 | car | bad |
| 19 | 31 | male | 2 | own | quite rich | NA | 3430 | 24 | radio/TV | good |
| 20 | 48 | male | 2 | own | little | NA | 2134 | 9 | car | good |
| 21 | 44 | male | 2 | rent | quite rich | little | 2647 | 6 | radio/TV | good |
| 22 | 48 | male | 1 | rent | little | little | 2241 | 10 | car | good |
| 23 | 44 | male | 2 | own | moderate | moderate | 1804 | 12 | car | good |
| 24 | 26 | male | 2 | own | NA | NA | 2069 | 10 | furniture/equipment | good |
| 25 | 36 | male | 1 | own | little | little | 1374 | 6 | furniture/equipment | good |
| 26 | 39 | male | 1 | own | little | NA | 426 | 6 | radio/TV | good |
| 27 | 42 | female | 2 | rent | rich | rich | 409 | 12 | radio/TV | good |
| 28 | 34 | male | 2 | own | little | moderate | 2415 | 7 | radio/TV | good |
| 29 | 63 | male | 2 | own | little | little | 6836 | 60 | business | bad |
In [30]:
import pandas as pd
import numpy as np
from sklearn import preprocessing
import matplotlib.pyplot as plt
plt.rc("font", size=14)
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
import seaborn as sns
sns.set(style="white")
sns.set(style="whitegrid", color_codes=True)
In [31]:
def display(obj):
cv2.imshow("show",obj)
cv2.waitKey(0)
cv2.destroyAllWindows()
b=edges.shape[0]
c=edges.shape[1]
#for i in range(b):
# for j in range(c):
# D=edges[i][j]
# #print(str(i)+","+str(j)+"="+str(D))
return img
def myresize(obj,b,c):
dim = (b, c)
resized = cv2.resize(obj, dim, interpolation = cv2.INTER_AREA)
return resized
def resshape(img):
width = int(img.shape[0])
height = int(img.shape[1])
wh=width * height
dim = (wh, 1)
resized = cv2.resize(img, dim, interpolation = cv2.INTER_AREA)
return resized
def uk(obj):
width = int(obj.shape[0])
height = int(obj.shape[1])
print (width ,' x ' , height)
return (width ,' x ' , height)
def uk2(obj):
width =len(obj[0])
height = len(obj[1])
print (width ,' x ' , height)
return (width ,' x ' , height)
def uk3(obj):
s =obj.shape()
return s
def model(obj):
lap=type(obj)
print(lap)
return lap
In [32]:
data=pd.read_csv('GD\\mycsv_test.csv',header=0) #pandas.core.frame.DataFrame 4521 x 17
data=data.dropna()
print(data.columns)
print(list(data.columns))
#['age;"job";"marital";"education";"default";"balance";"housing";"loan";"contact";"day";"month";"duration";"campaign";"pdays";"previous";"poutcome";"y"']
data.head()
Out[32]:
In [50]:
model(data)
list(data)
Out[50]:
In [37]:
data['Risk'].unique()
Out[37]:
In [19]:
#data['education']=np.where(data['education'] =='basic.9y', 'Basic', data['education'])
#data['education']=np.where(data['education'] =='basic.6y', 'Basic', data['education'])
#data['education']=np.where(data['education'] =='basic.4y', 'Basic', data['education'])
#data['y'].value_counts()
In [38]:
sns.countplot(x='Risk',data=data,palette='hls')
plt.show()
plt.savefig('count_plot')
In [39]:
sns.countplot(x='Purpose',data=data,palette='hls')
plt.show()
plt.savefig('count_plot')
In [40]:
jno= len(data[data['Risk']=='good'])
jyes = len(data[data['Risk']=='bad'])
total=jno + jyes
pct_of_no_sub = jno/(total)
print("percentage of no subscription is", pct_of_no_sub*100)
pct_of_sub = jyes/(total)
print("percentage of subscription", pct_of_sub*100)
In [42]:
data.groupby('Risk').mean()
Out[42]:
In [43]:
data.groupby('Purpose').mean()
Out[43]:
In [44]:
data.groupby('Sex').mean()
Out[44]:
In [45]:
%matplotlib inline
pd.crosstab(data.Sex,data.Risk).plot(kind='bar')
plt.title('Purchase Frequency for Job Title')
plt.xlabel('gender')
plt.ylabel('Frequency of Purchase')
plt.savefig('Gender of Purchase')
In [46]:
%matplotlib inline
pd.crosstab(data.Housing,data.Risk).plot(kind='bar')
plt.title('Purchase Frequency for Housing Title')
plt.xlabel('Housing')
plt.ylabel('Frequency of Purchase')
plt.savefig('purchase_fre_Housing')
In [52]:
%matplotlib inline
pd.crosstab(data.Housing,data.Risk).plot(kind='bar')
plt.title('Purchase Frequency for Credit amount Title')
plt.xlabel('Credit amount')
plt.ylabel('Frequency of Purchase')
plt.savefig('Purchase_Credit amount')
In [ ]:
In [ ]:
Tidak ada komentar:
Posting Komentar