File size: 5,462 Bytes
424caf8 56f36cc 424caf8 56f36cc 424caf8 002ceab 9d69630 424caf8 56f36cc 424caf8 002ceab 9d69630 424caf8 56f36cc 002ceab 9d69630 56f36cc 424caf8 002ceab 9d69630 424caf8 56f36cc 424caf8 56f36cc 424caf8 56f36cc 424caf8 56f36cc 424caf8 002ceab 9d69630 424caf8 56f36cc 424caf8 56f36cc |
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 |
import pandas as pd
from utils.utils_vars import SiteAnalysisData, UtilsVars
GSM_COLUMNS = [
"code",
"site_name",
"site_config_band",
"Region",
"number_trx_per_site",
"Longitude",
"Latitude",
"Hauteur",
"City",
"Adresse",
"Commune",
"Cercle",
]
WCDMA_COLUMNS = [
"code",
"site_name",
"Region",
"site_config_band",
"Longitude",
"Latitude",
"Hauteur",
"City",
"Adresse",
"Commune",
"Cercle",
]
LTE_COLUMNS = [
"code",
"lnbts_name",
"site_config_band",
"Region",
"Longitude",
"Latitude",
"Hauteur",
"City",
"Adresse",
"Commune",
"Cercle",
]
CODE_COLUMNS = [
"code",
"Region",
"Longitude",
"Latitude",
"Hauteur",
"City",
"Adresse",
"Commune",
"Cercle",
]
def clean_bands(bands):
if pd.isna(bands):
return None
parts = [p for p in bands.split("/") if p != "nan"]
return "/".join(parts) if parts else None
def site_db():
gsm_df: pd.DataFrame = UtilsVars.all_db_dfs[0]
wcdma_df: pd.DataFrame = UtilsVars.all_db_dfs[3]
lte_fdd_df: pd.DataFrame = UtilsVars.all_db_dfs[4]
lte_tdd_df: pd.DataFrame = UtilsVars.all_db_dfs[5]
gsm_df = gsm_df[GSM_COLUMNS]
gsm_df = gsm_df.rename(
columns={
"code": "code",
"site_name": "gsm_name",
"site_config_band": "2G_Bands",
}
)
gsm_df.drop_duplicates(subset=["code"], keep="first", inplace=True)
wcdma_df = wcdma_df[WCDMA_COLUMNS]
wcdma_df = wcdma_df.rename(
columns={
"code": "code",
"site_name": "wcdma_name",
"site_config_band": "3G_Bands",
}
)
wcdma_df.drop_duplicates(subset=["code"], keep="first", inplace=True)
lte_fdd_df = lte_fdd_df[LTE_COLUMNS]
lte_tdd_df = lte_tdd_df[LTE_COLUMNS]
lte_df: pd.DataFrame = pd.concat([lte_fdd_df, lte_tdd_df], ignore_index=False)
lte_df = lte_df.rename(
columns={
"code": "code",
"lnbts_name": "lte_name",
"site_config_band": "4G_Bands",
}
)
lte_df.drop_duplicates(subset=["code"], keep="first", inplace=True)
################################# CODE DATAFRAME#############################
gsm_code_df: pd.DataFrame = (
gsm_df[CODE_COLUMNS].copy() if gsm_df is not None else pd.DataFrame()
)
wcdma_code_df: pd.DataFrame = (
wcdma_df[CODE_COLUMNS].copy() if wcdma_df is not None else pd.DataFrame()
)
lte_code_df: pd.DataFrame = (
lte_df[CODE_COLUMNS].copy() if lte_df is not None else pd.DataFrame()
)
code_df: pd.DataFrame = pd.concat(
[gsm_code_df, wcdma_code_df, lte_code_df], ignore_index=True
)
code_df.drop_duplicates(subset=["code"], keep="first", inplace=True)
code_df.dropna(subset=["code"], inplace=True)
# order by code
code_df.sort_values(by=["code"], inplace=True)
# print(code_df)
# ################################# SITE DATAFRAME#############################
gsm_df_final = gsm_df[
[
"code",
"gsm_name",
"2G_Bands",
"number_trx_per_site",
]
].copy()
wcdma_df_final = wcdma_df[["code", "wcdma_name", "3G_Bands"]].copy()
lte_df_final = lte_df[["code", "lte_name", "4G_Bands"]].copy()
site_df = pd.merge(code_df, gsm_df_final, how="left", on="code")
site_df = pd.merge(site_df, wcdma_df_final, how="left", on="code")
site_df = pd.merge(site_df, lte_df_final, how="left", on="code")
# order by code
site_df["site_name"] = (
site_df["gsm_name"].fillna(site_df["wcdma_name"]).fillna(site_df["lte_name"])
)
site_df["all_bands"] = (
(site_df[["2G_Bands", "3G_Bands", "4G_Bands"]])
.astype(str)
.apply("/".join, axis=1)
)
site_df["all_bands"] = site_df["all_bands"].apply(clean_bands)
site_df = site_df[
[
"code",
"site_name",
"Region",
"2G_Bands",
"3G_Bands",
"4G_Bands",
"all_bands",
"number_trx_per_site",
"Longitude",
"Latitude",
"Hauteur",
"City",
"Adresse",
"Commune",
"Cercle",
]
]
site_df.sort_values(by=["code"], inplace=True)
UtilsVars.all_db_dfs.append(site_df)
UtilsVars.all_db_dfs_names.append("SITE")
####################### SITE ANALYSIS ###################################################
SiteAnalysisData.total_number_of_site = len(site_df["code"].unique())
SiteAnalysisData.total_munber_of_gsm_site = site_df["2G_Bands"].notna().sum()
SiteAnalysisData.total_number_of_wcdma_site = site_df["3G_Bands"].notna().sum()
SiteAnalysisData.total_number_of_lte_site = site_df["4G_Bands"].notna().sum()
SiteAnalysisData.gsm_bands_distribution = site_df["2G_Bands"].value_counts(
ascending=True
)
SiteAnalysisData.wcdma_bands_distribution = site_df["3G_Bands"].value_counts(
ascending=True
)
SiteAnalysisData.lte_bands_distribution = site_df["4G_Bands"].value_counts(
ascending=True
)
SiteAnalysisData.all_bands_distribution = site_df["all_bands"].value_counts(
ascending=True
)
SiteAnalysisData.number_of_trx_per_site_distribution = site_df[
"number_trx_per_site"
].value_counts()
|