Spaces:
Sleeping
Sleeping
File size: 2,162 Bytes
9e9465a |
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 78 79 80 81 |
import joblib
import pandas as pd
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import make_column_transformer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import train_test_split, RandomizedSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report
data_df = pd.read_csv("Bank_Telemarketing.csv")
target = 'subscribed'
numerical_features = ['Age', 'Duration(Sec)', 'CC Contact Freq', 'Days Since PC','PC Contact Freq']
categorical_features = ['Job', 'Marital Status', 'Education', 'Defaulter', 'Home Loan',
'Personal Loan', 'Communication Type', 'Last Contacted', 'Day of Week',
'PC Outcome']
print("Creating data subsets")
X = data_df[numerical_features + categorical_features]
y = data_df[target]
Xtrain, Xtest, ytrain, ytest = train_test_split(
X, y,
test_size=0.2,
random_state=42
)
numerical_pipeline = Pipeline([
('imputer', SimpleImputer(strategy='median')),
('scaler', StandardScaler())
])
categorical_pipeline = Pipeline([
('imputer', SimpleImputer(strategy='most_frequent')),
('onehot', OneHotEncoder(handle_unknown='ignore'))
])
preprocessor = make_column_transformer(
(numerical_pipeline, numerical_features),
(categorical_pipeline, categorical_features)
)
model_logistic_regression = LogisticRegression(n_jobs=-1)
print("Estimating Best Model Pipeline")
model_pipeline = make_pipeline(
preprocessor,
model_logistic_regression
)
param_distribution = {
"logisticregression__C": [0.001, 0.01, 0.1, 0.5, 1, 5, 10]
}
rand_search_cv = RandomizedSearchCV(
model_pipeline,
param_distribution,
n_iter=3,
cv=3,
random_state=42
)
rand_search_cv.fit(Xtrain, ytrain)
print("Logging Metrics")
print(f"Accuracy: {rand_search_cv.best_score_}")
print("Serializing Model")
saved_model_path = "model.joblib"
joblib.dump(rand_search_cv.best_estimator_, saved_model_path)
|