File size: 1,800 Bytes
b7d3682 fabb2c0 b7d3682 7f67122 b7d3682 fabb2c0 b7d3682 1cea5f0 b7d3682 6195581 f364b27 1cea5f0 b7d3682 7f67122 b7d3682 7f67122 |
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 |
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from joblib import load
from sklearn.preprocessing import MinMaxScaler
from sklearn.ensemble import VotingClassifier
from xgboost import XGBClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
class SmokerModel:
"""
Smoker Model Class that can predict new instances
INPUTS
---
model_path: the path to the model file
scaler_path: the path to the min max scaler file
"""
def __init__(self, model_path, scaler_path):
self.model = load(model_path)
self.scaler = load(scaler_path)
self.labels = ["non-smoker", "smoker"]
def scale(self, X):
"""
Apply the scaler used to train the model to the new data
INPUT
-----
X: the data to be scaled
OUTPUT
------
returns the scaled data
"""
new_data_scaled = self.scaler.transform(X)
return new_data_scaled
def predict(self, X: pd.DataFrame) -> str:
"""
Make a prediction on one sample using the loaded model.
INPUT
-----
X: the data to predict a label for
OUTPUT
------
predicted label
"""
# scale the data
X_scaled = self.scale(X)
#check array only has one sample
if X.shape[0] != 1:
raise ValueError("Input array must contain only one sample, but {} samples were found".format(X.shape[0]))
return
# Now, use the scaled data to make predictions using the loaded model
array = self.model.predict(X_scaled)
#predict
predicted_label = array[0]
str_label = self.labels[predicted_label]
return str_label |