File size: 12,848 Bytes
d269960 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 |
import numpy as np
import pandas as pd
from queries.process_gsm import combined_gsm_database
from utils.check_sheet_exist import execute_checks_sheets_exist
from utils.convert_to_excel import convert_dfs, save_dataframe
from utils.kpi_analysis_utils import (
GsmAnalysis,
create_daily_date,
create_dfs_per_kpi,
create_hourly_date,
kpi_naming_cleaning,
)
class GsmCapacity:
final_results = None
GSM_COLUMNS = [
"ID_BTS",
"site_name",
"name",
"BSC",
"BCF",
"BTS",
"code",
"Region",
"adminState",
"frequencyBandInUse",
"amrSegLoadDepTchRateLower",
"amrSegLoadDepTchRateUpper",
"dedicatedGPRScapacity",
"defaultGPRScapacity",
"cellId",
"band",
"site_config_band",
"trxRfPower",
"BCCH",
"number_trx_per_cell",
"number_trx_per_bcf",
"TRX_TCH",
"MAL_TCH",
]
TRX_COLUMNS = [
"ID_BTS",
"number_tch_per_cell",
"number_sd_per_cell",
"number_bcch_per_cell",
"number_ccch_per_cell",
"number_cbc_per_cell",
"number_total_channels_per_cell",
"number_signals_per_cell",
]
KPI_COLUMNS = [
"date",
"BTS_name",
"TCH_availability_ratio",
"2G_Carried_Traffic",
"TCH_call_blocking",
"TCH_ABIS_FAIL_CALL_c001084",
"SDCCH_real_blocking",
]
BH_COLUMNS_FOR_CAPACITY = [
"Max_Traffic BH",
"Avg_Traffic BH",
"Max_tch_call_blocking BH",
"Avg_tch_call_blocking BH",
"number_of_days_with_tch_blocking_exceeded",
"Max_sdcch_real_blocking BH",
"Avg_sdcch_real_blocking BH",
"number_of_days_with_sdcch_blocking_exceeded",
]
def bh_tch_call_blocking_analysis(
df: pd.DataFrame,
number_of_kpi_days: int,
tch_blocking_threshold: int,
number_of_threshold_days: int,
) -> pd.DataFrame:
result_df = df.copy()
last_days_df = result_df.iloc[:, -number_of_kpi_days:]
# last_days_df = last_days_df.fillna(0)
result_df["Avg_tch_call_blocking BH"] = last_days_df.mean(axis=1).round(2)
result_df["Max_tch_call_blocking BH"] = last_days_df.max(axis=1)
# Count the number of days above threshold
result_df["number_of_days_with_tch_blocking_exceeded"] = last_days_df.apply(
lambda row: sum(1 for x in row if x >= tch_blocking_threshold), axis=1
)
return result_df
def bh_sdcch_call_blocking_analysis(
df: pd.DataFrame,
number_of_kpi_days: int,
sdcch_blocking_threshold: int,
number_of_threshold_days: int,
) -> pd.DataFrame:
result_df = df.copy()
last_days_df = result_df.iloc[:, -number_of_kpi_days:]
# last_days_df = last_days_df.fillna(0)
result_df["Avg_sdcch_real_blocking BH"] = last_days_df.mean(axis=1).round(2)
result_df["Max_sdcch_real_blocking BH"] = last_days_df.max(axis=1)
# Count the number of days above threshold
result_df["number_of_days_with_sdcch_blocking_exceeded"] = last_days_df.apply(
lambda row: sum(1 for x in row if x >= sdcch_blocking_threshold), axis=1
)
return result_df
def bh_traffic_analysis(
df: pd.DataFrame,
number_of_kpi_days: int,
) -> pd.DataFrame:
result_df = df.copy()
last_days_df = result_df.iloc[:, -number_of_kpi_days:]
# last_days_df = last_days_df.fillna(0)
result_df["Avg_Traffic BH"] = last_days_df.mean(axis=1).round(2)
result_df["Max_Traffic BH"] = last_days_df.max(axis=1)
return result_df
def bh_dfs_per_kpi(
df: pd.DataFrame,
number_of_kpi_days: int = 7,
tch_blocking_threshold: int = 0.50,
sdcch_blocking_threshold: int = 0.50,
number_of_threshold_days: int = 3,
) -> pd.DataFrame:
"""
Create pivoted DataFrames for each KPI and perform analysis.
Args:
df: DataFrame containing KPI data
number_of_kpi_days: Number of days to analyze
threshold: Utilization threshold percentage for flagging
number_of_threshold_days: Minimum days above threshold to flag for upgrade
Returns:
DataFrame with combined analysis results
"""
pivoted_kpi_dfs = {}
pivoted_kpi_dfs = create_dfs_per_kpi(
df=df,
pivot_date_column="date",
pivot_name_column="BTS_name",
kpi_columns_from=2,
)
tch_call_blocking_df: pd.DataFrame = pivoted_kpi_dfs["TCH_call_blocking"]
sdcch_real_blocking_df: pd.DataFrame = pivoted_kpi_dfs["SDCCH_real_blocking"]
Carried_Traffic_df: pd.DataFrame = pivoted_kpi_dfs["2G_Carried_Traffic"]
tch_availability_ratio_df: pd.DataFrame = pivoted_kpi_dfs["TCH_availability_ratio"]
# ANALISYS
tch_call_blocking_df = bh_tch_call_blocking_analysis(
df=tch_call_blocking_df,
number_of_kpi_days=number_of_kpi_days,
tch_blocking_threshold=tch_blocking_threshold,
number_of_threshold_days=number_of_threshold_days,
)
sdcch_real_blocking_df = bh_sdcch_call_blocking_analysis(
df=sdcch_real_blocking_df,
number_of_kpi_days=number_of_kpi_days,
sdcch_blocking_threshold=sdcch_blocking_threshold,
number_of_threshold_days=number_of_threshold_days,
)
Carried_Traffic_df = bh_traffic_analysis(
df=Carried_Traffic_df,
number_of_kpi_days=number_of_kpi_days,
)
# Carried_Traffic_df["Max_Traffic BH"] = Carried_Traffic_df.max(axis=1)
# Carried_Traffic_df["Avg_Traffic BH"] = Carried_Traffic_df.mean(axis=1)
bh_kpi_df = pd.concat(
[
tch_availability_ratio_df,
Carried_Traffic_df,
tch_call_blocking_df,
sdcch_real_blocking_df,
],
axis=1,
)
# print(Carried_Traffic_df)
return bh_kpi_df
def analyse_bh_data(
bh_report_path: str,
number_of_kpi_days: int,
tch_blocking_threshold: int,
sdcch_blocking_threshold: int,
number_of_threshold_days: int,
) -> pd.DataFrame:
df = pd.read_csv(bh_report_path, delimiter=";")
df = kpi_naming_cleaning(df)
df = create_hourly_date(df)
df = df[KPI_COLUMNS]
df = bh_dfs_per_kpi(
df=df,
number_of_kpi_days=number_of_kpi_days,
tch_blocking_threshold=tch_blocking_threshold,
sdcch_blocking_threshold=sdcch_blocking_threshold,
number_of_threshold_days=number_of_threshold_days,
)
bh_df_for_capacity = df.copy()
bh_df_for_capacity = bh_df_for_capacity[BH_COLUMNS_FOR_CAPACITY]
bh_df_for_capacity = bh_df_for_capacity.reset_index()
# If columns have multiple levels (MultiIndex), flatten them
if isinstance(bh_df_for_capacity.columns, pd.MultiIndex):
bh_df_for_capacity.columns = [
"_".join([str(el) for el in col if el])
for col in bh_df_for_capacity.columns.values
]
# bh_df_for_capacity = bh_df_for_capacity.reset_index()
# rename Bts_name to name
bh_df_for_capacity = bh_df_for_capacity.rename(columns={"BTS_name": "name"})
return [bh_df_for_capacity, df]
def daily_dfs_per_kpi(
df: pd.DataFrame,
number_of_kpi_days: int = 7,
availability_threshold: int = 95,
number_of_threshold_days: int = 3,
tch_abis_fails_threshold: int = 10,
) -> pd.DataFrame:
"""
Create pivoted DataFrames for each KPI and perform analysis.
Args:
df: DataFrame containing KPI data
number_of_kpi_days: Number of days to analyze
threshold: Utilization threshold percentage for flagging
number_of_threshold_days: Minimum days above threshold to flag for upgrade
Returns:
DataFrame with combined analysis results
"""
pivoted_kpi_dfs = {}
pivoted_kpi_dfs = create_dfs_per_kpi(
df=df,
pivot_date_column="date",
pivot_name_column="BTS_name",
kpi_columns_from=2,
)
tch_call_blocking_df: pd.DataFrame = pivoted_kpi_dfs["TCH_call_blocking"]
sdcch_real_blocking_df: pd.DataFrame = pivoted_kpi_dfs["SDCCH_real_blocking"]
Carried_Traffic_df: pd.DataFrame = pivoted_kpi_dfs["2G_Carried_Traffic"]
tch_availability_ratio_df: pd.DataFrame = pivoted_kpi_dfs["TCH_availability_ratio"]
tch_abis_fails_df: pd.DataFrame = pivoted_kpi_dfs["TCH_ABIS_FAIL_CALL_c001084"]
def analyse_daily_data(
daily_report_path: str,
number_of_kpi_days: int,
tch_abis_fails_threshold: int,
availability_threshold: int,
number_of_threshold_days: int,
) -> pd.DataFrame:
df = pd.read_csv(daily_report_path, delimiter=";")
df = kpi_naming_cleaning(df)
df = create_daily_date(df)
df = df[KPI_COLUMNS]
df = daily_dfs_per_kpi(
df=df,
number_of_kpi_days=number_of_kpi_days,
availability_threshold=availability_threshold,
tch_abis_fails_threshold=tch_abis_fails_threshold,
number_of_threshold_days=number_of_threshold_days,
)
# print(df)
def get_gsm_databases(dump_path: str) -> pd.DataFrame:
dfs = combined_gsm_database(dump_path)
bts_df: pd.DataFrame = dfs[0]
trx_df: pd.DataFrame = dfs[2]
# Clean GSM df
bts_df = bts_df[GSM_COLUMNS]
trx_df = trx_df[TRX_COLUMNS]
# Remove duplicate in TRX df
trx_df = trx_df.drop_duplicates(subset=["ID_BTS"])
gsm_df = pd.merge(bts_df, trx_df, on="ID_BTS", how="left")
# add hf_rate_coef
gsm_df["hf_rate_coef"] = gsm_df["amrSegLoadDepTchRateLower"].map(
GsmAnalysis.hf_rate_coef
)
# Add "GPRS" colomn equal to (dedicatedGPRScapacity * number_tch_per_cell)/100
gsm_df["GPRS"] = (
gsm_df["dedicatedGPRScapacity"] * gsm_df["number_tch_per_cell"]
) / 100
# "TCH Actual HR%" equal to "number of TCH" multiplyed by "Coef HF rate"
gsm_df["TCH Actual HR%"] = gsm_df["number_tch_per_cell"] * gsm_df["hf_rate_coef"]
# Remove empty rows
gsm_df = gsm_df.dropna(subset=["TCH Actual HR%"])
# Get "Offered Traffic BH" by mapping approximate "TCH Actual HR%" to 2G analysis_utility "erlangB" dict
gsm_df["Offered Traffic BH"] = gsm_df["TCH Actual HR%"].apply(
lambda x: GsmAnalysis.erlangB_table.get(int(x), 0)
)
# save_dataframe(gsm_df, "GSM")
return gsm_df
def analyze_gsm_data(
dump_path: str,
daily_report_path: str,
bh_report_path: str,
number_of_kpi_days: int,
number_of_threshold_days: int,
availability_threshold: int,
tch_abis_fails_threshold: int,
sddch_blocking_threshold: float,
tch_blocking_threshold: float,
):
# print("Analyzing data...")
# print(f"Number of days: {number_of_kpi_days}")
# print(f"availability_threshold: {availability_threshold}")
analyse_daily_data(
daily_report_path=daily_report_path,
number_of_kpi_days=number_of_kpi_days,
availability_threshold=availability_threshold,
tch_abis_fails_threshold=tch_abis_fails_threshold,
number_of_threshold_days=number_of_threshold_days,
)
gsm_database_df: pd.DataFrame = get_gsm_databases(dump_path)
bh_kpi_dfs = analyse_bh_data(
bh_report_path=bh_report_path,
number_of_kpi_days=number_of_kpi_days,
tch_blocking_threshold=tch_blocking_threshold,
sdcch_blocking_threshold=sddch_blocking_threshold,
number_of_threshold_days=number_of_threshold_days,
)
bh_kpi_df = bh_kpi_dfs[0]
bh_kpi_full_df = bh_kpi_dfs[1]
gsm_analysis_df = gsm_database_df.merge(bh_kpi_df, on="name", how="left")
# "TCH UTILIZATION (@Max Traffic)" equal to "(Max_Trafic" divided by "Offered Traffic BH)*100"
gsm_analysis_df["TCH UTILIZATION (@Max Traffic)"] = (
gsm_analysis_df["Max_Traffic BH"] / gsm_analysis_df["Offered Traffic BH"]
) * 100
# Add "ERLANGB value" =MAX TRAFFIC/(1-(MAX TCH call blocking/200))
gsm_analysis_df["ErlabngB_value"] = gsm_analysis_df["Max_Traffic BH"] / (
1 - (gsm_analysis_df["Max_tch_call_blocking BH"] / 200)
)
# - Get "Target FR CHs" by mapping "ERLANG value" to 2G analysis_utility "erlangB" dict
gsm_analysis_df["Target FR CHs"] = gsm_analysis_df["ErlabngB_value"].apply(
lambda x: GsmAnalysis.erlangB_table.get(int(x) if pd.notnull(x) else 0, 0)
)
# "Target HR CHs" equal to "Target FR CHs" * 2
gsm_analysis_df["Target HR CHs"] = gsm_analysis_df["Target FR CHs"] * 2
# - Target TCHs equal to Target HR CHs + Signal + GPRS + SDCCH
gsm_analysis_df["Target TCHs"] = (
gsm_analysis_df["Target HR CHs"]
+ gsm_analysis_df["number_signals_per_cell"]
+ gsm_analysis_df["GPRS"]
+ gsm_analysis_df["number_sd_per_cell"]
)
# "Target TRXs" equal to roundup(Target TCHs/8)
gsm_analysis_df["Target TRXs"] = np.ceil(
gsm_analysis_df["Target TCHs"] / 8
) # df["Target TCHs"] / 8
# "Numberof required TRXs" equal to difference between "Target TRXs" and "number_trx_per_cell"
gsm_analysis_df["Numberof required TRXs"] = (
gsm_analysis_df["Target TRXs"] - gsm_analysis_df["number_trx_per_cell"]
)
return [gsm_analysis_df, bh_kpi_full_df]
|