File size: 3,656 Bytes
5fe24db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import xgboost as xgb\n",
    "model_path = \"model.None\"\n",
    "model = xgb.Booster()\n",
    "model.load_model(model_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "dv_path = \"dv.bin\"\n",
    "with open(dv_path, 'rb') as f_out:\n",
    "    dv = pickle.load(f_out)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler_path = \"scaler.bin\"\n",
    "with open(scaler_path, 'rb') as f_out:\n",
    "    scaler = pickle.load(f_out)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "def preprocess(data):\n",
    "    \"\"\"Preprocessing of the data\"\"\"\n",
    "    # turn json input to dataframe\n",
    "    data = pd.DataFrame([data])\n",
    "\n",
    "    # define numerical and categorical features\n",
    "    numerical = [\"X1\", \"X2\", \"X3\", \"X4\", \"X5\", \"X7\"]\n",
    "    categorical = [\"X6\", \"X8\"]\n",
    "\n",
    "    # preprocess numerical features\n",
    "    X_num = scaler.transform(data[numerical])\n",
    "    # preprocess categorical features\n",
    "    data[categorical] = data[categorical].astype(\"string\")\n",
    "    X_dicts = data[categorical].to_dict(orient=\"records\")\n",
    "    X_cat = dv.transform(X_dicts)\n",
    "    # concatenate both\n",
    "    X = np.concatenate((X_num, X_cat), axis=1)\n",
    "\n",
    "    return X\n",
    "\n",
    "\n",
    "def predict(X):\n",
    "    \"\"\"make predictions\"\"\"\n",
    "    pred = model.predict(X)\n",
    "    print('prediction', pred[0])\n",
    "    return float(pred[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "def main(input_data):\n",
    "    \"\"\"request input, preprocess it and make prediction\"\"\"\n",
    "    features = preprocess(input_data)\n",
    "    features_2 = xgb.DMatrix(features)\n",
    "    pred = predict(features_2)\n",
    "\n",
    "    result = {'heat load': pred}\n",
    "\n",
    "    return result\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "prediction 15.648413\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'heat load': 15.648412704467773}"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "input_example = {\n",
    "    \"X1\": 0.98,\n",
    "    \"X2\": 514.50,\n",
    "    \"X3\": 294.00,\n",
    "    \"X4\": 110.25,\n",
    "    \"X5\": 7.00,\n",
    "    \"X6\": 2,\n",
    "    \"X7\": 0.00,\n",
    "    \"X8\": 0,\n",
    "}\n",
    "\n",
    "main(input_example)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "mlops",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.8"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}