blueAI

Sleeping

App Files Files Community

ruchi commited on Aug 23, 2024

Commit

e9b921a

•

1 Parent(s): ba3a2e0

Add customer needs and sustainability

Browse files

Files changed (4) hide show

app.py +26 -4
money_needs.sqlite → data.sqlite +0 -0
notebook.ipynb +584 -0
utils.py +64 -29

app.py CHANGED Viewed

@@ -5,7 +5,7 @@ import google.generativeai as genai
 GOOGLE_API_KEY= os.getenv('GEMINI_API_KEY')
 genai.configure(api_key=GOOGLE_API_KEY)
 model = genai.GenerativeModel(model_name = "gemini-pro")
-from utils import findTop3MoneyNeeds, findTop3Topologies
 # Create a banner using Markdown
@@ -27,8 +27,8 @@ selectedCity = st.selectbox("Please select the City and the Bank Product for You
 selectedProduct = st.selectbox("Please select the Product", ["Current", "Mortage", "Credit Card", "Crypto"])
 subscriberTakeOut = st.number_input("Please enter your subscriber take out")
 moneyNeeds = st.text_area("Describe money needs of your target audience. For example do they spend a lot on education, healthcare, gym, eating out etc.")
-#customerExperience = st.text_area("Describe the customer experience needs of your target audience.")
-#sutainabilityNeeds = st.text_area("Describe the sutainability needs of your target audience.")
 userProposal = st.text_area("Enter your final Proposition for Select City and Product")
 submit_button = st.button("Submit")
@@ -105,14 +105,29 @@ if submit_button:
     topMoneyNeeds, topMoneyNeedsDict = findTop3MoneyNeeds(moneyNeeds)
     matchingTopologies, topologyDetails = findTop3Topologies(proposal, demographic)
     response = model.generate_content([pre_prompt.format(proposal)])
     st.write("As per your money needs your product is mostly targeting the below spending patterns",)
     for idx, need in enumerate(topMoneyNeeds):
         st.write("{}. {}".format(idx+1, need))
     st.write("As per your demographic and your proposition here are the three topologies you are targeting",)
@@ -125,7 +140,14 @@ if submit_button:
         sumTopology = 0
         for moneyNeed in topMoneyNeedsDict:
             sumTopology = sumTopology+int(moneyNeed[topology])
-        topologySumDict[topology] = sumTopology
     for topology in matchingTopologies:
         st.write("{}. {}".format(topology, topologySumDict[topology]))

 GOOGLE_API_KEY= os.getenv('GEMINI_API_KEY')
 genai.configure(api_key=GOOGLE_API_KEY)
 model = genai.GenerativeModel(model_name = "gemini-pro")
+from utils import findTop3MoneyNeeds, findTop3Topologies, findTop3CustomerExperienceNeeds, findTop3SustainabilityNeeds
 # Create a banner using Markdown
 selectedProduct = st.selectbox("Please select the Product", ["Current", "Mortage", "Credit Card", "Crypto"])
 subscriberTakeOut = st.number_input("Please enter your subscriber take out")
 moneyNeeds = st.text_area("Describe money needs of your target audience. For example do they spend a lot on education, healthcare, gym, eating out etc.")
+customerExperience = st.text_area("Describe the customer experience needs of your target audience.")
+sutainabilityNeeds = st.text_area("Describe the sutainability needs of your target audience.")
 userProposal = st.text_area("Enter your final Proposition for Select City and Product")
 submit_button = st.button("Submit")
     topMoneyNeeds, topMoneyNeedsDict = findTop3MoneyNeeds(moneyNeeds)
+    topCustomerExp, topCustomerExpDict = findTop3CustomerExperienceNeeds(customerExperience)
+    topSustainabilityNeeds, topSustainabilityNeedsDict = findTop3SustainabilityNeeds(sutainabilityNeeds)
     matchingTopologies, topologyDetails = findTop3Topologies(proposal, demographic)
     response = model.generate_content([pre_prompt.format(proposal)])
     st.write("As per your money needs your product is mostly targeting the below spending patterns",)
     for idx, need in enumerate(topMoneyNeeds):
         st.write("{}. {}".format(idx+1, need))
+    st.write("As per your money needs your product is mostly targeting the below spending patterns",)
+    for idx, exp in enumerate(topCustomerExp):
+        st.write("{}. {}".format(idx+1, exp))
+    st.write("As per your sustainability needs your product is mostly targeting the below spending patterns",)
+    for idx, need in enumerate(topSustainabilityNeeds):
+        st.write("{}. {}".format(idx+1, need))
     st.write("As per your demographic and your proposition here are the three topologies you are targeting",)
         sumTopology = 0
         for moneyNeed in topMoneyNeedsDict:
             sumTopology = sumTopology+int(moneyNeed[topology])
+        for customerExp in topCustomerExpDict:
+            sumTopology = sumTopology+int(customerExp[topology])
+        for sustainabilityNeed in topSustainabilityNeedsDict:
+            sumTopology = sumTopology+int(sustainabilityNeed[topology])
+        topologySumDict[topology] = math.floor(sumTopology/3)
     for topology in matchingTopologies:
         st.write("{}. {}".format(topology, topologySumDict[topology]))

money_needs.sqlite → data.sqlite RENAMED Viewed

Binary files a/money_needs.sqlite and b/data.sqlite differ

notebook.ipynb ADDED Viewed

	@@ -0,0 +1,584 @@

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mycsv = pd.read_csv('topologies_desc.csv',  encoding = \"ISO-8859-1\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Proportion Sample'"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mycsv[mycsv.columns[0]][0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'10%'"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mycsv['Ambitious Strivers'][0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mycsv = mycsv.dropna(axis=1, how='all')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Column1',\n",
+       " 'Ambitious Strivers',\n",
+       " 'Comfortable Altruistic',\n",
+       " 'Retired and liquid',\n",
+       " 'Living for Today',\n",
+       " 'Struggling Families',\n",
+       " 'High Wealth',\n",
+       " 'Money Managers',\n",
+       " 'Digital Pioneers',\n",
+       " 'Ultra High Wealth',\n",
+       " 'Unnamed: 10']"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "list(mycsv.columns).drop()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Column1',\n",
+       " 'Ambitious Strivers',\n",
+       " 'Comfortable Altruistic',\n",
+       " 'Retired and liquid',\n",
+       " 'Living for Today',\n",
+       " 'Struggling Families',\n",
+       " 'High Wealth',\n",
+       " 'Money Managers',\n",
+       " 'Digital Pioneers',\n",
+       " 'Ultra High Wealth']"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "list(mycsv.columns)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    Proportion Sample\n",
+       "1          Description\n",
+       "2     Household Income\n",
+       "3            dropout %\n",
+       "4    Propensity to Buy\n",
+       "Name: Column1, dtype: object"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mycsv['Column1']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1 = mycsv.loc[:, mycsv.columns != 'Column1']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Ambitious Strivers</th>\n",
+       "      <th>Comfortable Altruistic</th>\n",
+       "      <th>Retired and liquid</th>\n",
+       "      <th>Living for Today</th>\n",
+       "      <th>Struggling Families</th>\n",
+       "      <th>High Wealth</th>\n",
+       "      <th>Money Managers</th>\n",
+       "      <th>Digital Pioneers</th>\n",
+       "      <th>Ultra High Wealth</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>10%</td>\n",
+       "      <td>10%</td>\n",
+       "      <td>18%</td>\n",
+       "      <td>17%</td>\n",
+       "      <td>18%</td>\n",
+       "      <td>8%</td>\n",
+       "      <td>11%</td>\n",
+       "      <td>6%</td>\n",
+       "      <td>2%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Young ambitous professionals, mostly men, work...</td>\n",
+       "      <td>More to life than money; socially responsible;...</td>\n",
+       "      <td>Over 55, active pensioners, treat themselve to...</td>\n",
+       "      <td>Between 18 and 34 years old, independant, acce...</td>\n",
+       "      <td>Between the ages of 21 and 40 years old. In ma...</td>\n",
+       "      <td>Over 40 years old, independent, city dweling, ...</td>\n",
+       "      <td>Couples who enjoy managing their money, active...</td>\n",
+       "      <td>22- 35, Love exploring new ways to make money ...</td>\n",
+       "      <td>Extremely high net worth from inheritied money...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>£42K</td>\n",
+       "      <td>£64k</td>\n",
+       "      <td>£55K</td>\n",
+       "      <td>£24k</td>\n",
+       "      <td>£32K</td>\n",
+       "      <td>150k</td>\n",
+       "      <td>£55k</td>\n",
+       "      <td>£32K</td>\n",
+       "      <td>£750K+</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2%</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>10%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1.4</td>\n",
+       "      <td>1.2</td>\n",
+       "      <td>0.7</td>\n",
+       "      <td>0.5</td>\n",
+       "      <td>0.5</td>\n",
+       "      <td>0.9</td>\n",
+       "      <td>0.4</td>\n",
+       "      <td>1.2</td>\n",
+       "      <td>0.8</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                  Ambitious Strivers   \n",
+       "0                                                10%  \\\n",
+       "1  Young ambitous professionals, mostly men, work...   \n",
+       "2                                               £42K   \n",
+       "3                                                NaN   \n",
+       "4                                                1.4   \n",
+       "\n",
+       "                              Comfortable Altruistic   \n",
+       "0                                                10%  \\\n",
+       "1  More to life than money; socially responsible;...   \n",
+       "2                                               £64k   \n",
+       "3                                                 2%   \n",
+       "4                                                1.2   \n",
+       "\n",
+       "                                  Retired and liquid   \n",
+       "0                                                18%  \\\n",
+       "1  Over 55, active pensioners, treat themselve to...   \n",
+       "2                                               £55K   \n",
+       "3                                                NaN   \n",
+       "4                                                0.7   \n",
+       "\n",
+       "                                    Living for Today   \n",
+       "0                                                17%  \\\n",
+       "1  Between 18 and 34 years old, independant, acce...   \n",
+       "2                                               £24k   \n",
+       "3                                                NaN   \n",
+       "4                                                0.5   \n",
+       "\n",
+       "                                 Struggling Families   \n",
+       "0                                                18%  \\\n",
+       "1  Between the ages of 21 and 40 years old. In ma...   \n",
+       "2                                               £32K   \n",
+       "3                                                NaN   \n",
+       "4                                                0.5   \n",
+       "\n",
+       "                                         High Wealth   \n",
+       "0                                                 8%  \\\n",
+       "1  Over 40 years old, independent, city dweling, ...   \n",
+       "2                                               150k   \n",
+       "3                                                NaN   \n",
+       "4                                                0.9   \n",
+       "\n",
+       "                                      Money Managers   \n",
+       "0                                                11%  \\\n",
+       "1  Couples who enjoy managing their money, active...   \n",
+       "2                                               £55k   \n",
+       "3                                                NaN   \n",
+       "4                                                0.4   \n",
+       "\n",
+       "                                    Digital Pioneers   \n",
+       "0                                                 6%  \\\n",
+       "1  22- 35, Love exploring new ways to make money ...   \n",
+       "2                                               £32K   \n",
+       "3                                                NaN   \n",
+       "4                                                1.2   \n",
+       "\n",
+       "                                   Ultra High Wealth  \n",
+       "0                                                 2%  \n",
+       "1  Extremely high net worth from inheritied money...  \n",
+       "2                                             £750K+  \n",
+       "3                                                10%  \n",
+       "4                                                0.8  "
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list(mycsv.columns).remove('Column1')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Column1</th>\n",
+       "      <th>Ambitious Strivers</th>\n",
+       "      <th>Comfortable Altruistic</th>\n",
+       "      <th>Retired and liquid</th>\n",
+       "      <th>Living for Today</th>\n",
+       "      <th>Struggling Families</th>\n",
+       "      <th>High Wealth</th>\n",
+       "      <th>Money Managers</th>\n",
+       "      <th>Digital Pioneers</th>\n",
+       "      <th>Ultra High Wealth</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Proportion Sample</td>\n",
+       "      <td>10%</td>\n",
+       "      <td>10%</td>\n",
+       "      <td>18%</td>\n",
+       "      <td>17%</td>\n",
+       "      <td>18%</td>\n",
+       "      <td>8%</td>\n",
+       "      <td>11%</td>\n",
+       "      <td>6%</td>\n",
+       "      <td>2%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Description</td>\n",
+       "      <td>Young ambitous professionals, mostly men, work...</td>\n",
+       "      <td>More to life than money; socially responsible;...</td>\n",
+       "      <td>Over 55, active pensioners, treat themselve to...</td>\n",
+       "      <td>Between 18 and 34 years old, independant, acce...</td>\n",
+       "      <td>Between the ages of 21 and 40 years old. In ma...</td>\n",
+       "      <td>Over 40 years old, independent, city dweling, ...</td>\n",
+       "      <td>Couples who enjoy managing their money, active...</td>\n",
+       "      <td>22- 35, Love exploring new ways to make money ...</td>\n",
+       "      <td>Extremely high net worth from inheritied money...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Household Income</td>\n",
+       "      <td>£42K</td>\n",
+       "      <td>£64k</td>\n",
+       "      <td>£55K</td>\n",
+       "      <td>£24k</td>\n",
+       "      <td>£32K</td>\n",
+       "      <td>150k</td>\n",
+       "      <td>£55k</td>\n",
+       "      <td>£32K</td>\n",
+       "      <td>£750K+</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>dropout %</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2%</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>10%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Propensity to Buy</td>\n",
+       "      <td>1.4</td>\n",
+       "      <td>1.2</td>\n",
+       "      <td>0.7</td>\n",
+       "      <td>0.5</td>\n",
+       "      <td>0.5</td>\n",
+       "      <td>0.9</td>\n",
+       "      <td>0.4</td>\n",
+       "      <td>1.2</td>\n",
+       "      <td>0.8</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             Column1                                 Ambitious Strivers   \n",
+       "0  Proportion Sample                                                10%  \\\n",
+       "1        Description  Young ambitous professionals, mostly men, work...   \n",
+       "2   Household Income                                               £42K   \n",
+       "3          dropout %                                                NaN   \n",
+       "4  Propensity to Buy                                                1.4   \n",
+       "\n",
+       "                              Comfortable Altruistic   \n",
+       "0                                                10%  \\\n",
+       "1  More to life than money; socially responsible;...   \n",
+       "2                                               £64k   \n",
+       "3                                                 2%   \n",
+       "4                                                1.2   \n",
+       "\n",
+       "                                  Retired and liquid   \n",
+       "0                                                18%  \\\n",
+       "1  Over 55, active pensioners, treat themselve to...   \n",
+       "2                                               £55K   \n",
+       "3                                                NaN   \n",
+       "4                                                0.7   \n",
+       "\n",
+       "                                    Living for Today   \n",
+       "0                                                17%  \\\n",
+       "1  Between 18 and 34 years old, independant, acce...   \n",
+       "2                                               £24k   \n",
+       "3                                                NaN   \n",
+       "4                                                0.5   \n",
+       "\n",
+       "                                 Struggling Families   \n",
+       "0                                                18%  \\\n",
+       "1  Between the ages of 21 and 40 years old. In ma...   \n",
+       "2                                               £32K   \n",
+       "3                                                NaN   \n",
+       "4                                                0.5   \n",
+       "\n",
+       "                                         High Wealth   \n",
+       "0                                                 8%  \\\n",
+       "1  Over 40 years old, independent, city dweling, ...   \n",
+       "2                                               150k   \n",
+       "3                                                NaN   \n",
+       "4                                                0.9   \n",
+       "\n",
+       "                                      Money Managers   \n",
+       "0                                                11%  \\\n",
+       "1  Couples who enjoy managing their money, active...   \n",
+       "2                                               £55k   \n",
+       "3                                                NaN   \n",
+       "4                                                0.4   \n",
+       "\n",
+       "                                    Digital Pioneers   \n",
+       "0                                                 6%  \\\n",
+       "1  22- 35, Love exploring new ways to make money ...   \n",
+       "2                                               £32K   \n",
+       "3                                                NaN   \n",
+       "4                                                1.2   \n",
+       "\n",
+       "                                   Ultra High Wealth  \n",
+       "0                                                 2%  \n",
+       "1  Extremely high net worth from inheritied money...  \n",
+       "2                                             £750K+  \n",
+       "3                                                10%  \n",
+       "4                                                0.8  "
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mycsv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Young ambitous professionals, mostly men, work hard play attitude, competitive with peers and treat themselves to expensive things, Independent, enjoy using the internet, searching for the best deal, not always brand loyal, look for the best solution case by case, want to be recognised for their achievements'"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mycsv['Ambitious Strivers'][pd.Index(mycsv['Column1']).get_loc('Description')]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

utils.py CHANGED Viewed

@@ -20,7 +20,9 @@ def load_json_from_string(json_string):
 def concatenate_keys(keys):
     concatenated_string = ""
     for i, d in enumerate(keys, start=1):
-        concatenated_string += f"{d} "
     return concatenated_string.strip()
 def transform_to_dict_of_dicts(columns, rows):
@@ -29,7 +31,7 @@ def transform_to_dict_of_dicts(columns, rows):
     # Iterate over each row
     for row in rows:
-        print(dict(row))
         # The first element of the row is the key for the outer dictionary
         outer_key = row[0].strip()
@@ -55,7 +57,7 @@ def transform_topologies_to_dict(columns, rows):
     # Iterate over each row
     for row in rows:
-        print(dict(row))
         # The first element of the row is the key for the outer dictionary
         outer_key = row[0].strip()
@@ -75,39 +77,69 @@ def transform_topologies_to_dict(columns, rows):
     return result
 def findTop3MoneyNeeds(proposition):
-    moneyNeeds, rows = fetch_db_rows_as_dicts('money_needs.sqlite', 'money_needs')
     moneyNeedsDict = transform_to_dict_of_dicts(moneyNeeds, rows)
-    print(list(moneyNeedsDict.keys()))
     needs = findTop3Needs(proposition, list(moneyNeedsDict.keys()))
     needDictIndexes = []
     for need in needs:
         needDictIndexes.append(moneyNeedsDict[need])
     print(needDictIndexes)
     return needs, needDictIndexes
-def findTop3Needs(proposition, moneyNeeds):
-    moneyNeedsString = concatenate_keys(moneyNeeds)
-    prompt = '''You have these listed needs of customers
     {}
     Now given a proposition
     "{}"
-    Find the best 3 strings out of the list which matches this proposition. Return output strictly only in json under a list called matches
     '''
-    moneyNeedsPrompt = prompt.format(moneyNeedsString, proposition)
-    response = model.generate_content([moneyNeedsPrompt])
     output = response.text
     output = output.replace('```json', '')
     output = output.replace('```', '')
     obj = load_json_from_string(output)
     print(obj)
-    return obj['matches']
 def findTop3Topologies(proposition, demographic):
@@ -156,36 +188,39 @@ def findTop3Topologies(proposition, demographic):
     return obj['matches'], topologyDetails
-def findTop3Needs(proposition, moneyNeeds):
-    moneyNeedsString = concatenate_keys(moneyNeeds)
-    prompt = '''You have these listed needs of customers
-    {}
-    Now given a proposition
-    "{}"
-    Find the best 3 strings out of the list which matches this proposition. Return output strictly only in json under a list called matches
-    '''
-    moneyNeedsPrompt = prompt.format(moneyNeedsString, proposition)
-    response = model.generate_content([moneyNeedsPrompt])
-    output = response.text
-    output = output.replace('```json', '')
-    output = output.replace('```', '')
-    obj = load_json_from_string(output)
-    print(obj)
-    return obj['matches']
 # findTop3Topologies('We have a product for family people giving them discounts and low interest loans for home appliances. They can pay us back in small instalments over the course of 4 years',
 #                    'CharlesTown city people are young families people mostly with a population of 20000. Out of this 65% are between the age of 30-45. Most of them have kids aged between 0-15')
-findTop3MoneyNeeds('We have a product for family people giving them discounts and low interest loans for home appliances. They can pay us back in small instalments over the course of 4 years')
 #We provide a credit card which gives 10% discount on purchasing home appliances and also provides low interest rates based loans
 # subscriber take out
 # 250 and below with a negative factor of 2.0

 def concatenate_keys(keys):
     concatenated_string = ""
     for i, d in enumerate(keys, start=1):
+        concatenated_string += f"{i}. {d}"
+    print('##########################')
+    print(concatenated_string.strip())
     return concatenated_string.strip()
 def transform_to_dict_of_dicts(columns, rows):
     # Iterate over each row
     for row in rows:
+        #print(dict(row))
         # The first element of the row is the key for the outer dictionary
         outer_key = row[0].strip()
     # Iterate over each row
     for row in rows:
+        #print(dict(row))
         # The first element of the row is the key for the outer dictionary
         outer_key = row[0].strip()
     return result
 def findTop3MoneyNeeds(proposition):
+    moneyNeeds, rows = fetch_db_rows_as_dicts('data.sqlite', 'money_needs')
     moneyNeedsDict = transform_to_dict_of_dicts(moneyNeeds, rows)
+    #print(list(moneyNeedsDict.keys()))
     needs = findTop3Needs(proposition, list(moneyNeedsDict.keys()))
     needDictIndexes = []
     for need in needs:
         needDictIndexes.append(moneyNeedsDict[need])
+    #print(needDictIndexes)
+    return needs, needDictIndexes
+def findTop3CustomerExperienceNeeds(proposition):
+    moneyNeeds, rows = fetch_db_rows_as_dicts('data.sqlite', 'customer_exp')
+    moneyNeedsDict = transform_to_dict_of_dicts(moneyNeeds, rows)
+    #print(list(moneyNeedsDict.keys()))
+    needs = findTop3Needs(proposition, list(moneyNeedsDict.keys()))
+    needDictIndexes = []
+    for need in needs:
+        needDictIndexes.append(moneyNeedsDict[need])
+    #print(needDictIndexes)
+    return needs, needDictIndexes
+def findTop3SustainabilityNeeds(proposition):
+    print(" Proposition sustain  = {}".format(proposition))
+    allNeeds, rows = fetch_db_rows_as_dicts('data.sqlite', 'sustainability')
+    needsDict = transform_to_dict_of_dicts(allNeeds, rows)
+    needs = findTop3Needs(proposition, list(needsDict.keys()))
+    needDictIndexes = []
+    print(list(needsDict.keys()))
+    for need in needs:
+        needDictIndexes.append(needsDict[need])
     print(needDictIndexes)
     return needs, needDictIndexes
+def findTop3Needs(proposition, needs):
+    needsString = concatenate_keys(needs)
+    prompt = '''You have this comma separated listed needs of customers
     {}
     Now given a proposition
     "{}"
+    Find the best 3 strings out of the above numbered list which best matches this proposition. Return in output only the number next to the matching string strictly only in json under a list called matches
     '''
+    needsPrompt = prompt.format(needsString, proposition)
+    print(needsPrompt)
+    response = model.generate_content([needsPrompt])
     output = response.text
     output = output.replace('```json', '')
     output = output.replace('```', '')
     obj = load_json_from_string(output)
     print(obj)
+    needsIndexes = [needs[int(idx)-1] for idx in obj['matches']]
+    return needsIndexes #obj['matches']
 def findTop3Topologies(proposition, demographic):
     return obj['matches'], topologyDetails
+# def findTop3Needs(proposition, moneyNeeds):
+#     moneyNeedsString = concatenate_keys(moneyNeeds)
+#     print(moneyNeedsString)
+#     prompt = '''You have these listed needs of customers
+#     {}
+#     Now given a proposition
+#     "{}"
+#     Find the best 3 strings out of the list which matches this proposition. Return output strictly only in json under a list called matches
+#     '''
+#     moneyNeedsPrompt = prompt.format(moneyNeedsString, proposition)
+#     response = model.generate_content([moneyNeedsPrompt])
+#     output = response.text
+#     output = output.replace('```json', '')
+#     output = output.replace('```', '')
+#     obj = load_json_from_string(output)
+#     print(obj)
+#     return obj['matches']
 # findTop3Topologies('We have a product for family people giving them discounts and low interest loans for home appliances. They can pay us back in small instalments over the course of 4 years',
 #                    'CharlesTown city people are young families people mostly with a population of 20000. Out of this 65% are between the age of 30-45. Most of them have kids aged between 0-15')
+#findTop3SustainabilityNeeds('We support Home appliances are all electric and use no fuel based energy')
 #We provide a credit card which gives 10% discount on purchasing home appliances and also provides low interest rates based loans
+#customer need - We provide our customer with utmost comfort and at home service
 # subscriber take out
 # 250 and below with a negative factor of 2.0