Spaces:
Runtime error
Runtime error
Upload 3 files
Browse files- model.joblib +3 -0
- requirements.txt +1 -0
- train.py +80 -0
model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c3c382c7233f0463a9c2698c7190fa6a89f2704433ae79735d9a6a1acfb5529
|
3 |
+
size 8439
|
requirements.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
scikit-learn==1.2.2
|
train.py
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
import joblib
|
3 |
+
import pandas as pd
|
4 |
+
|
5 |
+
from sklearn.preprocessing import StandardScaler, OneHotEncoder
|
6 |
+
from sklearn.compose import make_column_transformer
|
7 |
+
from sklearn.impute import SimpleImputer
|
8 |
+
from sklearn.pipeline import Pipeline
|
9 |
+
from sklearn.pipeline import make_pipeline
|
10 |
+
|
11 |
+
from sklearn.model_selection import train_test_split, RandomizedSearchCV
|
12 |
+
|
13 |
+
from sklearn.linear_model import LogisticRegression
|
14 |
+
from sklearn.metrics import accuracy_score, classification_report
|
15 |
+
|
16 |
+
data_df = pd.read_csv("Bank_Telemarketing.csv")
|
17 |
+
|
18 |
+
target = 'subscribed'
|
19 |
+
numerical_features = ['Age', 'Duration(Sec)', 'CC Contact Freq', 'Days Since PC','PC Contact Freq']
|
20 |
+
categorical_features = ['Job', 'Marital Status', 'Education', 'Defaulter', 'Home Loan',
|
21 |
+
'Personal Loan', 'Communication Type', 'Last Contacted', 'Day of Week',
|
22 |
+
'PC Outcome']
|
23 |
+
|
24 |
+
print("Creating data subsets")
|
25 |
+
|
26 |
+
X = data_df[numerical_features + categorical_features]
|
27 |
+
y = data_df[target]
|
28 |
+
|
29 |
+
Xtrain, Xtest, ytrain, ytest = train_test_split(
|
30 |
+
X, y,
|
31 |
+
test_size=0.2,
|
32 |
+
random_state=42
|
33 |
+
)
|
34 |
+
|
35 |
+
numerical_pipeline = Pipeline([
|
36 |
+
('imputer', SimpleImputer(strategy='median')),
|
37 |
+
('scaler', StandardScaler())
|
38 |
+
])
|
39 |
+
|
40 |
+
categorical_pipeline = Pipeline([
|
41 |
+
('imputer', SimpleImputer(strategy='most_frequent')),
|
42 |
+
('onehot', OneHotEncoder(handle_unknown='ignore'))
|
43 |
+
])
|
44 |
+
|
45 |
+
preprocessor = make_column_transformer(
|
46 |
+
(numerical_pipeline, numerical_features),
|
47 |
+
(categorical_pipeline, categorical_features)
|
48 |
+
)
|
49 |
+
|
50 |
+
model_logistic_regression = LogisticRegression(n_jobs=-1)
|
51 |
+
|
52 |
+
print("Estimating Best Model Pipeline")
|
53 |
+
|
54 |
+
model_pipeline = make_pipeline(
|
55 |
+
preprocessor,
|
56 |
+
model_logistic_regression
|
57 |
+
)
|
58 |
+
|
59 |
+
param_distribution = {
|
60 |
+
"logisticregression__C": [0.001, 0.01, 0.1, 0.5, 1, 5, 10]
|
61 |
+
}
|
62 |
+
|
63 |
+
rand_search_cv = RandomizedSearchCV(
|
64 |
+
model_pipeline,
|
65 |
+
param_distribution,
|
66 |
+
n_iter=3,
|
67 |
+
cv=3,
|
68 |
+
random_state=42
|
69 |
+
)
|
70 |
+
|
71 |
+
rand_search_cv.fit(Xtrain, ytrain)
|
72 |
+
|
73 |
+
print("Logging Metrics")
|
74 |
+
print(f"Accuracy: {rand_search_cv.best_score_}")
|
75 |
+
|
76 |
+
print("Serializing Model")
|
77 |
+
|
78 |
+
saved_model_path = "model.joblib"
|
79 |
+
|
80 |
+
joblib.dump(rand_search_cv.best_estimator_, saved_model_path)
|