user_client2024/154
1
0
Fork 0
generated from user_client2024/78
Code Issues Pull Requests Packages Projects Releases Wiki Activity

System save at 23/05/2025 20:44 by user_client2024

Browse Source
This commit is contained in:
user_client2024 2025-05-23 15:14:13 +00:00
parent cd8cc24134
commit 1fc6a20fff
3 changed files with 138 additions and 138 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

92
.ipynb_checkpoints/main-checkpoint.ipynb
View File

@ -159,58 +159,58 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"def trx_count_sum_groupwise(data_filt_partywise): \n", "# def trx_count_sum_groupwise(data_filt_partywise): \n",
" data_filt_partywise = data_filt_partywise.sort_values(by='transaction_amount') \n", "# data_filt_partywise = data_filt_partywise.sort_values(by='transaction_amount') \n",
" groupeddata = pd.DataFrame(columns=['group_no', 'trxn_cnt', 'trxn_sum_amt', \n", "# groupeddata = pd.DataFrame(columns=['group_no', 'trxn_cnt', 'trxn_sum_amt', \n",
" 'MIN_LIMIT', 'PCT_RANGE'])\n", "# 'MIN_LIMIT', 'PCT_RANGE'])\n",
" \n", " \n",
" trxns = data_filt_partywise['transaction_amount'].values\n", "# trxns = data_filt_partywise['transaction_amount'].values\n",
" pct_range = data_filt_partywise['PCT_RANGE'].max()\n", "# pct_range = data_filt_partywise['PCT_RANGE'].max()\n",
" min_value = data_filt_partywise['MIN_LIMIT'].max()\n", "# min_value = data_filt_partywise['MIN_LIMIT'].max()\n",
"\n", "\n",
" trxns = trxns[trxns >= min_value]\n", "# trxns = trxns[trxns >= min_value]\n",
" if len(trxns) > 0:\n", "# if len(trxns) > 0:\n",
" min_value = trxns[0]\n", "# min_value = trxns[0]\n",
"\n", "\n",
" group_count = 0\n", "# group_count = 0\n",
" while len(trxns) > 0:\n", "# while len(trxns) > 0:\n",
" max_value = min_value + (pct_range * 0.01 * min_value)\n", "# max_value = min_value + (pct_range * 0.01 * min_value)\n",
" mask = np.logical_and(trxns >= min_value, trxns <= max_value)\n", "# mask = np.logical_and(trxns >= min_value, trxns <= max_value)\n",
" group_filter_trx = trxns[mask]\n", "# group_filter_trx = trxns[mask]\n",
" trx_count = len(group_filter_trx)\n", "# trx_count = len(group_filter_trx)\n",
" trx_sum = np.sum(group_filter_trx)\n", "# trx_sum = np.sum(group_filter_trx)\n",
" group_count += 1\n", "# group_count += 1\n",
" groupeddata.loc[len(groupeddata)] = [group_count, trx_count, trx_sum, \n", "# groupeddata.loc[len(groupeddata)] = [group_count, trx_count, trx_sum, \n",
" min_value, pct_range]\n", "# min_value, pct_range]\n",
" trxns = trxns[trxns > max_value]\n", "# trxns = trxns[trxns > max_value]\n",
" if len(trxns) > 0:\n", "# if len(trxns) > 0:\n",
" min_value = trxns[0]\n", "# min_value = trxns[0]\n",
"\n", "\n",
" return groupeddata.to_dict('list')\n", "# return groupeddata.to_dict('list')\n",
"\n", "\n",
"# ---------------------------\n", "# # ---------------------------\n",
"# Function 4: Run scenario 9\n", "# # Function 4: Run scenario 9\n",
"# ---------------------------\n", "# # ---------------------------\n",
"def scenario9_data(data1): \n", "# def scenario9_data(data1): \n",
" grouped = data1.groupby('Focal_id')[['transaction_amount', 'MIN_LIMIT', 'PCT_RANGE']].apply(\n", "# grouped = data1.groupby('Focal_id')[['transaction_amount', 'MIN_LIMIT', 'PCT_RANGE']].apply(\n",
" trx_count_sum_groupwise).reset_index()\n", "# trx_count_sum_groupwise).reset_index()\n",
"\n", "\n",
" df_list = []\n", "# df_list = []\n",
" for i in grouped.index:\n", "# for i in grouped.index:\n",
" df_party = pd.DataFrame(grouped.iloc[i, -1])\n", "# df_party = pd.DataFrame(grouped.iloc[i, -1])\n",
" df_party['Focal_id'] = grouped.loc[i, 'Focal_id']\n", "# df_party['Focal_id'] = grouped.loc[i, 'Focal_id']\n",
" df_list.append(df_party)\n", "# df_list.append(df_party)\n",
"\n", "\n",
" final_df = pd.concat(df_list, ignore_index=True) \n", "# final_df = pd.concat(df_list, ignore_index=True) \n",
" Segment = data1.groupby('Focal_id')['Segment'].agg('max').reset_index()\n", "# Segment = data1.groupby('Focal_id')['Segment'].agg('max').reset_index()\n",
" Risk = data1.groupby('Focal_id')['Risk'].agg('max').reset_index()\n", "# Risk = data1.groupby('Focal_id')['Risk'].agg('max').reset_index()\n",
" SAR_FLAG = data1.groupby('Focal_id')['SAR_FLAG'].agg('max').reset_index()\n", "# SAR_FLAG = data1.groupby('Focal_id')['SAR_FLAG'].agg('max').reset_index()\n",
" \n", " \n",
" final_df = final_df.merge(Segment,on = 'Focal_id', how = 'left')\n", "# final_df = final_df.merge(Segment,on = 'Focal_id', how = 'left')\n",
" final_df = final_df.merge(Risk,on = 'Focal_id', how = 'left')\n", "# final_df = final_df.merge(Risk,on = 'Focal_id', how = 'left')\n",
" final_df = final_df.merge(SAR_FLAG,on = 'Focal_id', how = 'left')\n", "# final_df = final_df.merge(SAR_FLAG,on = 'Focal_id', how = 'left')\n",
" \n", " \n",
" return final_df\n", "# return final_df\n",
" " " "
] ]
}, },
@ -253,10 +253,10 @@
" ]\n", " ]\n",
" df = pd.DataFrame(row_list, columns = cols)\n", " df = pd.DataFrame(row_list, columns = cols)\n",
" df['Segment'] = 'SME'\n", " df['Segment'] = 'SME'\n",
" df['MIN_LIMIT'] = 50000\n", "# df['MIN_LIMIT'] = 50000\n",
" df['PCT_RANGE'] = 20\n", "# df['PCT_RANGE'] = 20\n",
" \n", " \n",
" scenario_data = scenario9_data(df)\n", "# scenario_data = scenario9_data(df)\n",
" \n", " \n",
" return scenario_data" " return scenario_data"
] ]

92
main.ipynb
View File

@ -159,58 +159,58 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"def trx_count_sum_groupwise(data_filt_partywise): \n", "# def trx_count_sum_groupwise(data_filt_partywise): \n",
" data_filt_partywise = data_filt_partywise.sort_values(by='transaction_amount') \n", "# data_filt_partywise = data_filt_partywise.sort_values(by='transaction_amount') \n",
" groupeddata = pd.DataFrame(columns=['group_no', 'trxn_cnt', 'trxn_sum_amt', \n", "# groupeddata = pd.DataFrame(columns=['group_no', 'trxn_cnt', 'trxn_sum_amt', \n",
" 'MIN_LIMIT', 'PCT_RANGE'])\n", "# 'MIN_LIMIT', 'PCT_RANGE'])\n",
" \n", " \n",
" trxns = data_filt_partywise['transaction_amount'].values\n", "# trxns = data_filt_partywise['transaction_amount'].values\n",
" pct_range = data_filt_partywise['PCT_RANGE'].max()\n", "# pct_range = data_filt_partywise['PCT_RANGE'].max()\n",
" min_value = data_filt_partywise['MIN_LIMIT'].max()\n", "# min_value = data_filt_partywise['MIN_LIMIT'].max()\n",
"\n", "\n",
" trxns = trxns[trxns >= min_value]\n", "# trxns = trxns[trxns >= min_value]\n",
" if len(trxns) > 0:\n", "# if len(trxns) > 0:\n",
" min_value = trxns[0]\n", "# min_value = trxns[0]\n",
"\n", "\n",
" group_count = 0\n", "# group_count = 0\n",
" while len(trxns) > 0:\n", "# while len(trxns) > 0:\n",
" max_value = min_value + (pct_range * 0.01 * min_value)\n", "# max_value = min_value + (pct_range * 0.01 * min_value)\n",
" mask = np.logical_and(trxns >= min_value, trxns <= max_value)\n", "# mask = np.logical_and(trxns >= min_value, trxns <= max_value)\n",
" group_filter_trx = trxns[mask]\n", "# group_filter_trx = trxns[mask]\n",
" trx_count = len(group_filter_trx)\n", "# trx_count = len(group_filter_trx)\n",
" trx_sum = np.sum(group_filter_trx)\n", "# trx_sum = np.sum(group_filter_trx)\n",
" group_count += 1\n", "# group_count += 1\n",
" groupeddata.loc[len(groupeddata)] = [group_count, trx_count, trx_sum, \n", "# groupeddata.loc[len(groupeddata)] = [group_count, trx_count, trx_sum, \n",
" min_value, pct_range]\n", "# min_value, pct_range]\n",
" trxns = trxns[trxns > max_value]\n", "# trxns = trxns[trxns > max_value]\n",
" if len(trxns) > 0:\n", "# if len(trxns) > 0:\n",
" min_value = trxns[0]\n", "# min_value = trxns[0]\n",
"\n", "\n",
" return groupeddata.to_dict('list')\n", "# return groupeddata.to_dict('list')\n",
"\n", "\n",
"# ---------------------------\n", "# # ---------------------------\n",
"# Function 4: Run scenario 9\n", "# # Function 4: Run scenario 9\n",
"# ---------------------------\n", "# # ---------------------------\n",
"def scenario9_data(data1): \n", "# def scenario9_data(data1): \n",
" grouped = data1.groupby('Focal_id')[['transaction_amount', 'MIN_LIMIT', 'PCT_RANGE']].apply(\n", "# grouped = data1.groupby('Focal_id')[['transaction_amount', 'MIN_LIMIT', 'PCT_RANGE']].apply(\n",
" trx_count_sum_groupwise).reset_index()\n", "# trx_count_sum_groupwise).reset_index()\n",
"\n", "\n",
" df_list = []\n", "# df_list = []\n",
" for i in grouped.index:\n", "# for i in grouped.index:\n",
" df_party = pd.DataFrame(grouped.iloc[i, -1])\n", "# df_party = pd.DataFrame(grouped.iloc[i, -1])\n",
" df_party['Focal_id'] = grouped.loc[i, 'Focal_id']\n", "# df_party['Focal_id'] = grouped.loc[i, 'Focal_id']\n",
" df_list.append(df_party)\n", "# df_list.append(df_party)\n",
"\n", "\n",
" final_df = pd.concat(df_list, ignore_index=True) \n", "# final_df = pd.concat(df_list, ignore_index=True) \n",
" Segment = data1.groupby('Focal_id')['Segment'].agg('max').reset_index()\n", "# Segment = data1.groupby('Focal_id')['Segment'].agg('max').reset_index()\n",
" Risk = data1.groupby('Focal_id')['Risk'].agg('max').reset_index()\n", "# Risk = data1.groupby('Focal_id')['Risk'].agg('max').reset_index()\n",
" SAR_FLAG = data1.groupby('Focal_id')['SAR_FLAG'].agg('max').reset_index()\n", "# SAR_FLAG = data1.groupby('Focal_id')['SAR_FLAG'].agg('max').reset_index()\n",
" \n", " \n",
" final_df = final_df.merge(Segment,on = 'Focal_id', how = 'left')\n", "# final_df = final_df.merge(Segment,on = 'Focal_id', how = 'left')\n",
" final_df = final_df.merge(Risk,on = 'Focal_id', how = 'left')\n", "# final_df = final_df.merge(Risk,on = 'Focal_id', how = 'left')\n",
" final_df = final_df.merge(SAR_FLAG,on = 'Focal_id', how = 'left')\n", "# final_df = final_df.merge(SAR_FLAG,on = 'Focal_id', how = 'left')\n",
" \n", " \n",
" return final_df\n", "# return final_df\n",
" " " "
] ]
}, },
@ -253,10 +253,10 @@
" ]\n", " ]\n",
" df = pd.DataFrame(row_list, columns = cols)\n", " df = pd.DataFrame(row_list, columns = cols)\n",
" df['Segment'] = 'SME'\n", " df['Segment'] = 'SME'\n",
" df['MIN_LIMIT'] = 50000\n", "# df['MIN_LIMIT'] = 50000\n",
" df['PCT_RANGE'] = 20\n", "# df['PCT_RANGE'] = 20\n",
" \n", " \n",
" scenario_data = scenario9_data(df)\n", "# scenario_data = scenario9_data(df)\n",
" \n", " \n",
" return scenario_data" " return scenario_data"
] ]

92
main.py
View File

@ -142,58 +142,58 @@ query = """
# In[20]: # In[20]:
def trx_count_sum_groupwise(data_filt_partywise): # def trx_count_sum_groupwise(data_filt_partywise):
data_filt_partywise = data_filt_partywise.sort_values(by='transaction_amount') # data_filt_partywise = data_filt_partywise.sort_values(by='transaction_amount')
groupeddata = pd.DataFrame(columns=['group_no', 'trxn_cnt', 'trxn_sum_amt', # groupeddata = pd.DataFrame(columns=['group_no', 'trxn_cnt', 'trxn_sum_amt',
'MIN_LIMIT', 'PCT_RANGE']) # 'MIN_LIMIT', 'PCT_RANGE'])
trxns = data_filt_partywise['transaction_amount'].values # trxns = data_filt_partywise['transaction_amount'].values
pct_range = data_filt_partywise['PCT_RANGE'].max() # pct_range = data_filt_partywise['PCT_RANGE'].max()
min_value = data_filt_partywise['MIN_LIMIT'].max() # min_value = data_filt_partywise['MIN_LIMIT'].max()
trxns = trxns[trxns >= min_value] # trxns = trxns[trxns >= min_value]
if len(trxns) > 0: # if len(trxns) > 0:
min_value = trxns[0] # min_value = trxns[0]
group_count = 0 # group_count = 0
while len(trxns) > 0: # while len(trxns) > 0:
max_value = min_value + (pct_range * 0.01 * min_value) # max_value = min_value + (pct_range * 0.01 * min_value)
mask = np.logical_and(trxns >= min_value, trxns <= max_value) # mask = np.logical_and(trxns >= min_value, trxns <= max_value)
group_filter_trx = trxns[mask] # group_filter_trx = trxns[mask]
trx_count = len(group_filter_trx) # trx_count = len(group_filter_trx)
trx_sum = np.sum(group_filter_trx) # trx_sum = np.sum(group_filter_trx)
group_count += 1 # group_count += 1
groupeddata.loc[len(groupeddata)] = [group_count, trx_count, trx_sum, # groupeddata.loc[len(groupeddata)] = [group_count, trx_count, trx_sum,
min_value, pct_range] # min_value, pct_range]
trxns = trxns[trxns > max_value] # trxns = trxns[trxns > max_value]
if len(trxns) > 0: # if len(trxns) > 0:
min_value = trxns[0] # min_value = trxns[0]
return groupeddata.to_dict('list') # return groupeddata.to_dict('list')
# --------------------------- # # ---------------------------
# Function 4: Run scenario 9 # # Function 4: Run scenario 9
# --------------------------- # # ---------------------------
def scenario9_data(data1): # def scenario9_data(data1):
grouped = data1.groupby('Focal_id')[['transaction_amount', 'MIN_LIMIT', 'PCT_RANGE']].apply( # grouped = data1.groupby('Focal_id')[['transaction_amount', 'MIN_LIMIT', 'PCT_RANGE']].apply(
trx_count_sum_groupwise).reset_index() # trx_count_sum_groupwise).reset_index()
df_list = [] # df_list = []
for i in grouped.index: # for i in grouped.index:
df_party = pd.DataFrame(grouped.iloc[i, -1]) # df_party = pd.DataFrame(grouped.iloc[i, -1])
df_party['Focal_id'] = grouped.loc[i, 'Focal_id'] # df_party['Focal_id'] = grouped.loc[i, 'Focal_id']
df_list.append(df_party) # df_list.append(df_party)
final_df = pd.concat(df_list, ignore_index=True) # final_df = pd.concat(df_list, ignore_index=True)
Segment = data1.groupby('Focal_id')['Segment'].agg('max').reset_index() # Segment = data1.groupby('Focal_id')['Segment'].agg('max').reset_index()
Risk = data1.groupby('Focal_id')['Risk'].agg('max').reset_index() # Risk = data1.groupby('Focal_id')['Risk'].agg('max').reset_index()
SAR_FLAG = data1.groupby('Focal_id')['SAR_FLAG'].agg('max').reset_index() # SAR_FLAG = data1.groupby('Focal_id')['SAR_FLAG'].agg('max').reset_index()
final_df = final_df.merge(Segment,on = 'Focal_id', how = 'left') # final_df = final_df.merge(Segment,on = 'Focal_id', how = 'left')
final_df = final_df.merge(Risk,on = 'Focal_id', how = 'left') # final_df = final_df.merge(Risk,on = 'Focal_id', how = 'left')
final_df = final_df.merge(SAR_FLAG,on = 'Focal_id', how = 'left') # final_df = final_df.merge(SAR_FLAG,on = 'Focal_id', how = 'left')
return final_df # return final_df
@ -229,10 +229,10 @@ class Scenario:
] ]
df = pd.DataFrame(row_list, columns = cols) df = pd.DataFrame(row_list, columns = cols)
df['Segment'] = 'SME' df['Segment'] = 'SME'
df['MIN_LIMIT'] = 50000 # df['MIN_LIMIT'] = 50000
df['PCT_RANGE'] = 20 # df['PCT_RANGE'] = 20
scenario_data = scenario9_data(df) # scenario_data = scenario9_data(df)
return scenario_data return scenario_data