File size: 4,553 Bytes
2f4f4ef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
266bd2c
2f4f4ef
 
b49bc9c
 
 
 
 
 
 
 
2f4f4ef
 
 
 
 
 
266bd2c
2f4f4ef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
266bd2c
2f4f4ef
 
 
ccada5d
 
 
 
 
 
 
 
 
 
266bd2c
 
 
 
 
 
 
 
 
 
 
 
2f4f4ef
 
 
 
 
 
 
 
 
 
 
266bd2c
2f4f4ef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
266bd2c
2f4f4ef
 
 
 
266bd2c
 
 
 
 
2f4f4ef
 
 
 
 
 
 
 
 
 
 
 
b49bc9c
2f4f4ef
 
 
b49bc9c
2f4f4ef
 
 
 
 
 
649875f
2f4f4ef
 
 
 
b49bc9c
2f4f4ef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Indicator Harmonizer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The goal of this code is to provide a recommendation of indicators and detect cases where we migh need to create new"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1 Load required packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Functions loaded\n",
      "Functions loaded\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<module 'functions' from '/Users/alanfortunysicart/Documents/GitHub/IndicatorHarmonizer/functions.py'>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import re\n",
    "import numpy as np\n",
    "import importlib\n",
    "import importlib\n",
    "from seatable_api import Base, context\n",
    "from pandas import json_normalize\n",
    "import importlib\n",
    "import functions as f\n",
    "importlib.reload(f)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2. Load the required data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load the request data including the generic indicator requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "table1 = pd.read_excel('/Users/alanfortunysicart/Downloads/Indicators_Indicators_Frameworks_Default View(1).xlsx')\n",
    "table2 = pd.read_excel('/Users/alanfortunysicart/Downloads/Indicators_Indicators_Default view(14).xlsx')\n",
    "# columns to use for embeddings on table 1\n",
    "\n",
    "columns_embeddings_col1 = ['Indicator Name']\n",
    "\n",
    "# columns to use for embeddings on table 2\n",
    "columns_embeddings_col2 = ['Indicator name (leonardo)']\n",
    "\n",
    "harmonization=True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "if 'Indicator ID' in table1.columns:\n",
    "    table1['ID'] = table1['Indicator ID'].astype(str)\n",
    "else:\n",
    "    table1['ID'] = table1['ID'].astype(str)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create a column concatenating the column's content to be used for the embeddings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "table1 = f.concatenate_columns(table1, columns=f.columns_embeddings_col1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Concatenate topic and indicator request name to help the indicator search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "table2 = f.concatenate_columns(table2,columns=f.columns_embeddings_col2)\n",
    "\n",
    "if 'Indicator ID' in table2.columns:\n",
    "    table2['ID'] = table2['Indicator ID'].astype(str)\n",
    "else:\n",
    "    table2['ID'] = table2['ID'].astype(str)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 3. Compute the similarity between leonardo. indicator and the requested names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "result_final = f.process_similarity_results(table1, table2, harmonization=True,columns_embeddings_col1=f.columns_embeddings_col1,columns_embeddings_col2=f.columns_embeddings_col2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 4. Export the results and submit"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "result_final.to_csv('Indicator_Framework_Harmonizer_Definition_new_order.csv')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "seatableToKobo",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}