user_client2024/185
1
0
Fork 0
generated from user_client2024/152
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

System save at 22/09/2025 17:03 by user_client2024

Browse Source
This commit is contained in:
user_client2024 2025-09-22 11:33:07 +00:00
parent 8a8c00ab77
commit 39dc2b32ef
3 changed files with 147 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
.ipynb_checkpoints/main-checkpoint.ipynb
View File

@ -11,6 +11,49 @@
"import pandas as pd\n",
"from tms_data_interface import SQLQueryInterface\n",
"\n",
"def apply_sar_flag(df, var1, var2, var3, random_state=42):\n",
" \"\"\"\n",
" Apply percentile-based thresholds, split data into alerting and non-alerting,\n",
" flag random 10% of alerting data as 'Y', and merge back.\n",
"\n",
" Parameters:\n",
" df (pd.DataFrame): Input dataframe\n",
" var1 (str): First variable (for 50th percentile threshold)\n",
" var2 (str): Second variable (for 50th percentile threshold)\n",
" var3 (str): Third variable (for 90th percentile threshold)\n",
" random_state (int): Seed for reproducibility\n",
"\n",
" Returns:\n",
" pd.DataFrame: DataFrame with 'SAR_Flag' column added\n",
" \"\"\"\n",
"\n",
" # Calculate thresholds\n",
" th1 = np.percentile(df[var1].dropna(), 50)\n",
" th2 = np.percentile(df[var2].dropna(), 50)\n",
" th3 = np.percentile(df[var3].dropna(), 90)\n",
"\n",
" # Split into alerting and non-alerting\n",
" alerting = df[(df[var1] >= th1) &\n",
" (df[var2] >= th2) &\n",
" (df[var3] >= th3)].copy()\n",
"\n",
" non_alerting = df.loc[~df.index.isin(alerting.index)].copy()\n",
"\n",
" # Assign SAR_Flag = 'N' for non-alerting\n",
" non_alerting['SAR_Flag'] = 'N'\n",
"\n",
" # Assign SAR_Flag for alerting data\n",
" alerting['SAR_Flag'] = 'N'\n",
" n_y = int(len(alerting) * 0.1) # 10% count\n",
" if n_y > 0:\n",
" y_indices = alerting.sample(n=n_y, random_state=random_state).index\n",
" alerting.loc[y_indices, 'SAR_Flag'] = 'Y'\n",
"\n",
" # Merge back and preserve original order\n",
" final_df = pd.concat([alerting, non_alerting]).sort_index()\n",
"\n",
" return final_df\n",
"\n",
"query = \"\"\"\n",
"WITH time_windows AS (\n",
" SELECT\n",
@ -107,9 +150,14 @@
" final_scenario_df['PARTICIPANT_VOLUME_PCT'] = final_scenario_df['PARTICIPANT_VOLUME']/\\\n",
" final_scenario_df['TOTAL_VOLUME'] * 100\n",
" final_scenario_df['Segment'] = 'Default'\n",
" final_scenario_df['SAR_FLAG'] = 'N'\n",
" # final_scenario_df['SAR_FLAG'] = 'N'\n",
" final_scenario_df['Risk'] = 'Medium Risk'\n",
" final_scenario_df.dropna(inplace=True)\n",
" final_scenario_df = apply_sar_flag(final_scenario_df,\n",
" 'PRICE_CHANGE_PCT',\n",
" 'PARTICIPANT_VOLUME_PCT',\n",
" 'TOTAL_VOLUME',\n",
" random_state=42)\n",
" # final_scenario_df['RUN_DATE'] = final_scenario_df['END_DATE']\n",
" return final_scenario_df\n"
]

50
main.ipynb
View File

@ -11,6 +11,49 @@
"import pandas as pd\n",
"from tms_data_interface import SQLQueryInterface\n",
"\n",
"def apply_sar_flag(df, var1, var2, var3, random_state=42):\n",
" \"\"\"\n",
" Apply percentile-based thresholds, split data into alerting and non-alerting,\n",
" flag random 10% of alerting data as 'Y', and merge back.\n",
"\n",
" Parameters:\n",
" df (pd.DataFrame): Input dataframe\n",
" var1 (str): First variable (for 50th percentile threshold)\n",
" var2 (str): Second variable (for 50th percentile threshold)\n",
" var3 (str): Third variable (for 90th percentile threshold)\n",
" random_state (int): Seed for reproducibility\n",
"\n",
" Returns:\n",
" pd.DataFrame: DataFrame with 'SAR_Flag' column added\n",
" \"\"\"\n",
"\n",
" # Calculate thresholds\n",
" th1 = np.percentile(df[var1].dropna(), 50)\n",
" th2 = np.percentile(df[var2].dropna(), 50)\n",
" th3 = np.percentile(df[var3].dropna(), 90)\n",
"\n",
" # Split into alerting and non-alerting\n",
" alerting = df[(df[var1] >= th1) &\n",
" (df[var2] >= th2) &\n",
" (df[var3] >= th3)].copy()\n",
"\n",
" non_alerting = df.loc[~df.index.isin(alerting.index)].copy()\n",
"\n",
" # Assign SAR_Flag = 'N' for non-alerting\n",
" non_alerting['SAR_Flag'] = 'N'\n",
"\n",
" # Assign SAR_Flag for alerting data\n",
" alerting['SAR_Flag'] = 'N'\n",
" n_y = int(len(alerting) * 0.1) # 10% count\n",
" if n_y > 0:\n",
" y_indices = alerting.sample(n=n_y, random_state=random_state).index\n",
" alerting.loc[y_indices, 'SAR_Flag'] = 'Y'\n",
"\n",
" # Merge back and preserve original order\n",
" final_df = pd.concat([alerting, non_alerting]).sort_index()\n",
"\n",
" return final_df\n",
"\n",
"query = \"\"\"\n",
"WITH time_windows AS (\n",
" SELECT\n",
@ -107,9 +150,14 @@
" final_scenario_df['PARTICIPANT_VOLUME_PCT'] = final_scenario_df['PARTICIPANT_VOLUME']/\\\n",
" final_scenario_df['TOTAL_VOLUME'] * 100\n",
" final_scenario_df['Segment'] = 'Default'\n",
" final_scenario_df['SAR_FLAG'] = 'N'\n",
" # final_scenario_df['SAR_FLAG'] = 'N'\n",
" final_scenario_df['Risk'] = 'Medium Risk'\n",
" final_scenario_df.dropna(inplace=True)\n",
" final_scenario_df = apply_sar_flag(final_scenario_df,\n",
" 'PRICE_CHANGE_PCT',\n",
" 'PARTICIPANT_VOLUME_PCT',\n",
" 'TOTAL_VOLUME',\n",
" random_state=42)\n",
" # final_scenario_df['RUN_DATE'] = final_scenario_df['END_DATE']\n",
" return final_scenario_df\n"
]

50
main.py
View File

@ -8,6 +8,49 @@ from datetime import datetime, timedelta
import pandas as pd
from tms_data_interface import SQLQueryInterface
def apply_sar_flag(df, var1, var2, var3, random_state=42):
"""
Apply percentile-based thresholds, split data into alerting and non-alerting,
flag random 10% of alerting data as 'Y', and merge back.
Parameters:
df (pd.DataFrame): Input dataframe
var1 (str): First variable (for 50th percentile threshold)
var2 (str): Second variable (for 50th percentile threshold)
var3 (str): Third variable (for 90th percentile threshold)
random_state (int): Seed for reproducibility
Returns:
pd.DataFrame: DataFrame with 'SAR_Flag' column added
"""
# Calculate thresholds
th1 = np.percentile(df[var1].dropna(), 50)
th2 = np.percentile(df[var2].dropna(), 50)
th3 = np.percentile(df[var3].dropna(), 90)
# Split into alerting and non-alerting
alerting = df[(df[var1] >= th1) &
(df[var2] >= th2) &
(df[var3] >= th3)].copy()
non_alerting = df.loc[~df.index.isin(alerting.index)].copy()
# Assign SAR_Flag = 'N' for non-alerting
non_alerting['SAR_Flag'] = 'N'
# Assign SAR_Flag for alerting data
alerting['SAR_Flag'] = 'N'
n_y = int(len(alerting) * 0.1) # 10% count
if n_y > 0:
y_indices = alerting.sample(n=n_y, random_state=random_state).index
alerting.loc[y_indices, 'SAR_Flag'] = 'Y'
# Merge back and preserve original order
final_df = pd.concat([alerting, non_alerting]).sort_index()
return final_df
query = """
WITH time_windows AS (
SELECT
@ -104,9 +147,14 @@ class Scenario:
final_scenario_df['PARTICIPANT_VOLUME_PCT'] = final_scenario_df['PARTICIPANT_VOLUME']/\
final_scenario_df['TOTAL_VOLUME'] * 100
final_scenario_df['Segment'] = 'Default'
final_scenario_df['SAR_FLAG'] = 'N'
# final_scenario_df['SAR_FLAG'] = 'N'
final_scenario_df['Risk'] = 'Medium Risk'
final_scenario_df.dropna(inplace=True)
final_scenario_df = apply_sar_flag(final_scenario_df,
'PRICE_CHANGE_PCT',
'PARTICIPANT_VOLUME_PCT',
'TOTAL_VOLUME',
random_state=42)
# final_scenario_df['RUN_DATE'] = final_scenario_df['END_DATE']
return final_scenario_df