junshan-kit 2.2.7__py2.py3-none-any.whl → 2.2.9__py2.py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
junshan_kit/DataSets.py
CHANGED
|
@@ -11,7 +11,7 @@ import junshan_kit.DataProcessor
|
|
|
11
11
|
import junshan_kit.kit
|
|
12
12
|
from sklearn.preprocessing import StandardScaler
|
|
13
13
|
|
|
14
|
-
|
|
14
|
+
#----------------------------------------------------------
|
|
15
15
|
def download_data(data_name):
|
|
16
16
|
from junshan_kit.kit import JianguoyunDownloaderFirefox, JianguoyunDownloaderChrome
|
|
17
17
|
|
|
@@ -36,14 +36,7 @@ def download_data(data_name):
|
|
|
36
36
|
else:
|
|
37
37
|
print("❌ Invalid choice. Please enter 1 or 2.\n")
|
|
38
38
|
|
|
39
|
-
|
|
40
|
-
def credit_card_fraud_detection(data_name = "Credit Card Fraud Detection", print_info = False):
|
|
41
|
-
|
|
42
|
-
csv_path = f'./exp_data/{data_name}/creditcard.csv'
|
|
43
|
-
drop_cols = []
|
|
44
|
-
label_col = 'Class'
|
|
45
|
-
label_map = {0: -1, 1: 1}
|
|
46
|
-
|
|
39
|
+
def run(csv_path, data_name, drop_cols, label_col, label_map, print_info):
|
|
47
40
|
if not os.path.exists(csv_path):
|
|
48
41
|
print('\n' + '*'*60)
|
|
49
42
|
print(f"Please download the data.")
|
|
@@ -55,8 +48,72 @@ def credit_card_fraud_detection(data_name = "Credit Card Fraud Detection", print
|
|
|
55
48
|
df = cleaner.preprocess_dataset(csv_path, drop_cols, label_col, label_map, print_info=print_info)
|
|
56
49
|
|
|
57
50
|
return df
|
|
58
|
-
|
|
59
|
-
|
|
51
|
+
|
|
52
|
+
"""
|
|
53
|
+
----------------------------------------------------------------------
|
|
54
|
+
Datasets
|
|
55
|
+
----------------------------------------------------------------------
|
|
56
|
+
"""
|
|
57
|
+
|
|
58
|
+
def credit_card_fraud_detection(data_name = "Credit Card Fraud Detection", print_info = False):
|
|
59
|
+
|
|
60
|
+
csv_path = f'./exp_data/{data_name}/creditcard.csv'
|
|
61
|
+
drop_cols = []
|
|
62
|
+
label_col = 'diagnosed_diabetes'
|
|
63
|
+
label_map = {0: -1, 1: 1}
|
|
64
|
+
|
|
65
|
+
df = run(csv_path, data_name, drop_cols, label_col, label_map, print_info)
|
|
66
|
+
|
|
67
|
+
return df
|
|
68
|
+
|
|
69
|
+
|
|
70
|
+
def diabetes_health_indicators_dataset(data_name = "Diabetes Health Indicators Dataset", print_info = False):
|
|
71
|
+
csv_path = f'./exp_data/{data_name}/diabetes_dataset.csv'
|
|
72
|
+
drop_cols = []
|
|
73
|
+
label_col = 'Class'
|
|
74
|
+
label_map = {0: -1, 1: 1}
|
|
75
|
+
|
|
76
|
+
df = run(csv_path, data_name, drop_cols, label_col, label_map, print_info)
|
|
77
|
+
|
|
78
|
+
return df
|
|
79
|
+
|
|
80
|
+
|
|
81
|
+
def electric_vehicle_population_data(data_name = "Electric Vehicle Population Data", print_info = False):
|
|
82
|
+
csv_path = f'./exp_data/{data_name}/Electric_Vehicle_Population_Data.csv'
|
|
83
|
+
drop_cols = ['VIN (1-10)', 'DOL Vehicle ID', 'Vehicle Location']
|
|
84
|
+
label_col = 'Electric Vehicle Type'
|
|
85
|
+
label_map = {
|
|
86
|
+
'Battery Electric Vehicle (BEV)': 1,
|
|
87
|
+
'Plug-in Hybrid Electric Vehicle (PHEV)': -1
|
|
88
|
+
}
|
|
89
|
+
|
|
90
|
+
df = run(csv_path, data_name, drop_cols, label_col, label_map, print_info)
|
|
91
|
+
|
|
92
|
+
return df
|
|
93
|
+
|
|
94
|
+
def global_house_purchase_dataset(data_name = "Global House Purchase Dataset", print_info = False):
|
|
95
|
+
csv_path = f'./exp_data/{data_name}/global_house_purchase_dataset.csv'
|
|
96
|
+
drop_cols = ['property_id']
|
|
97
|
+
label_col = 'Electric Vehicle Type'
|
|
98
|
+
label_map = {0: -1, 1: 1}
|
|
99
|
+
|
|
100
|
+
df = run(csv_path, data_name, drop_cols, label_col, label_map, print_info)
|
|
101
|
+
|
|
102
|
+
return df
|
|
103
|
+
|
|
104
|
+
|
|
105
|
+
def health_lifestyle_dataset(data_name = "Health_lifestyle_dataset", print_info = False):
|
|
106
|
+
csv_path = f'./exp_data/{data_name}/health_lifestyle_dataset.csv'
|
|
107
|
+
drop_cols = ['id']
|
|
108
|
+
label_col = 'decision'
|
|
109
|
+
label_map = {0: -1, 1: 1}
|
|
110
|
+
|
|
111
|
+
df = run(csv_path, data_name, drop_cols, label_col, label_map, print_info)
|
|
112
|
+
|
|
113
|
+
return df
|
|
114
|
+
|
|
115
|
+
|
|
116
|
+
|
|
60
117
|
|
|
61
118
|
|
|
62
119
|
def wine_and_food_pairing_dataset():
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
junshan_kit/DataProcessor.py,sha256=eryVmS5BFZj8wjDN2QWVHqkbFgFuWU0HXV9s6TGf9QM,4442
|
|
2
|
+
junshan_kit/DataSets.py,sha256=BNlXUbsautITelxp35uHSYSq2bTbIbqLyQnmqapaeDc,3963
|
|
3
|
+
junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
4
|
+
junshan_kit/kit.py,sha256=tB1TpW9hW1EweK1RQwHOdUo7uG1QU4vSeyR0fdaSydo,9569
|
|
5
|
+
junshan_kit-2.2.9.dist-info/METADATA,sha256=oIytayt1Z9OpFOJl8_7cYMl3li3KsphQfZDRqsqat8g,329
|
|
6
|
+
junshan_kit-2.2.9.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
|
|
7
|
+
junshan_kit-2.2.9.dist-info/RECORD,,
|
|
@@ -1,7 +0,0 @@
|
|
|
1
|
-
junshan_kit/DataProcessor.py,sha256=eryVmS5BFZj8wjDN2QWVHqkbFgFuWU0HXV9s6TGf9QM,4442
|
|
2
|
-
junshan_kit/DataSets.py,sha256=QOpHAJkDLWBXP31cG8BStrXZITJEBiTCB1brmAy4TBQ,1985
|
|
3
|
-
junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
4
|
-
junshan_kit/kit.py,sha256=tB1TpW9hW1EweK1RQwHOdUo7uG1QU4vSeyR0fdaSydo,9569
|
|
5
|
-
junshan_kit-2.2.7.dist-info/METADATA,sha256=LNjAHPrUu_tJs4HrYk2fyC-3GSb3UQj1c_4WIVYv7Wo,329
|
|
6
|
-
junshan_kit-2.2.7.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
|
|
7
|
-
junshan_kit-2.2.7.dist-info/RECORD,,
|
|
File without changes
|