-
Notifications
You must be signed in to change notification settings - Fork 242
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
b4f56c7
commit 3fb267c
Showing
4 changed files
with
100 additions
and
78 deletions.
There are no files selected for viewing
178 changes: 100 additions & 78 deletions
178
anyway/parsers/compare_cbs_and_anyway_road_segments_accidents.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,119 +1,141 @@ | ||
from anyway.models import AccidentMarkerView | ||
from anyway.widgets.widget_utils import get_expression_for_fields, get_expression_for_road_segment_location_fields, split_location_fields_and_others | ||
from anyway.models import AccidentMarkerView, RoadSegments | ||
from anyway.app_and_db import db | ||
from sqlalchemy import func, and_ | ||
import os | ||
import pandas as pd | ||
from tqdm import tqdm | ||
from anyway.models import AccidentMarkerView, RoadSegments | ||
from anyway.widgets.widget_utils import ( | ||
get_expression_for_fields, | ||
get_expression_for_road_segment_location_fields, | ||
split_location_fields_and_others, | ||
) | ||
from anyway.app_and_db import db | ||
from sqlalchemy import func | ||
|
||
# Constants | ||
CBS_TYPE_1_SUMMARY_FILE = os.path.join("static", "data", "cbs_summary_files", "2022", "t01_type_1_for_segment_test.xls") | ||
CBS_TYPE_3_SUMMARY_FILE = os.path.join("static", "data", "cbs_summary_files", "2022", "t03_type_3_for_segment_test.xls") | ||
OUTPUT_DIR = os.path.join("static", "data", "cbs_summary_files", "2022", "comparison_output") | ||
OUTPUT_FILE = os.path.join(OUTPUT_DIR, "cbs_anyway_road_segments.csv") | ||
|
||
CBS_TYPE_1_SUMMARY_FILE = "static/data/cbs_summary_files/t01_type_1_for_segment_test.xls" | ||
CBS_TYPE_3_SUMMARY_FILE = "static/data/cbs_summary_files/t03_type_3_for_segment_test.xls" | ||
# Global dictionary for road segments | ||
ROAD_SEGMENTS_DICT = {} | ||
|
||
|
||
def get_cbs_count(): | ||
df_type_1 = pd.read_excel(CBS_TYPE_1_SUMMARY_FILE, skiprows=4) | ||
df_type_1.columns = ["segment", "road", "from", "to", "acc_per_milion_km", "total", "total_light", "total_severe", "total_fatal", "2022_total", "2022_light", "2022_severe", "2022_fatal", "2021_total", "2020_total", "avg", "length"] | ||
df_type_1 = df_type_1.loc[df_type_1.segment.notna()] | ||
df_type_1 = df_type_1.loc[df_type_1.segment.astype(str).str.isdigit()] | ||
df_type_1["provider_code"] = 1 | ||
df_type_1["road_segment_name_cbs"] = df_type_1["from"] + "_" + df_type_1["to"] | ||
df_type_1_total = df_type_1[["road_segment_name_cbs", "road" , "segment","provider_code", "2020_total","2021_total", "2022_total"]].copy() | ||
df_type_1_total.columns = ["road_segment_name_cbs", "road" , "segment", "provider_code", "2020_cbs", "2021_cbs", "2022_cbs"] | ||
df_type_1_total[["2020_cbs", "2021_cbs", "2022_cbs"]] = df_type_1_total[["2020_cbs", "2021_cbs", "2022_cbs"]].fillna(0) | ||
def read_excel_file(file_path, skip_rows, columns, segment_col="segment"): | ||
try: | ||
df = pd.read_excel(file_path, skiprows=skip_rows) | ||
df.columns = columns | ||
df = df.loc[df[segment_col].notna() & df[segment_col].astype(str).str.isdigit()] | ||
return df | ||
except Exception as e: | ||
print(f"Error reading {file_path}: {e}") | ||
return pd.DataFrame() | ||
|
||
df_type_1_2022 = df_type_1[["road_segment_name_cbs", "road" , "segment", "provider_code", "2022_light", "2022_severe", "2022_fatal"]] | ||
|
||
def get_cbs_count(): | ||
df_type_1_columns = [ | ||
"segment", "road", "from", "to", "acc_per_million_km", "total", "total_light", | ||
"total_severe", "total_fatal", "2022_total", "2022_light", "2022_severe", "2022_fatal", | ||
"2021_total", "2020_total", "avg", "length" | ||
] | ||
df_type_3_columns = [ | ||
"segment", "road", "from", "to", "acc_per_million_km", "total", "2022_total", | ||
"2021_total", "2020_total", "avg", "length" | ||
] | ||
|
||
df_type_3 = pd.read_excel(CBS_TYPE_3_SUMMARY_FILE, skiprows=5) | ||
df_type_3.columns = ["segment", "road", "from", "to", "acc_per_milion_km", "total", "2022_total", "2021_total", "2020_total", "avg", "length"] | ||
df_type_3 = df_type_3.loc[df_type_3.segment.notna()] | ||
df_type_3 = df_type_3.loc[df_type_3.segment.astype(str).str.isdigit()] | ||
# Read and process type 1 data | ||
df_type_1 = read_excel_file(CBS_TYPE_1_SUMMARY_FILE, 4, df_type_1_columns) | ||
if df_type_1.empty: | ||
return pd.DataFrame() | ||
df_type_1["provider_code"] = 1 | ||
df_type_1["road_segment_name_cbs"] = df_type_1["from"].str.slice(start=1) + " -" + df_type_1["to"].str.slice(start=2) | ||
df_type_1_total = df_type_1[["road_segment_name_cbs", "road", "segment", "provider_code", "2020_total", "2021_total", "2022_total"]].copy() | ||
df_type_1_total.columns = ["road_segment_name_cbs", "road", "segment", "provider_code", "2020_cbs", "2021_cbs", "2022_cbs"] | ||
df_type_1_total.fillna({"2020_cbs": 0, "2021_cbs": 0, "2022_cbs": 0}, inplace=True) | ||
|
||
# Read and process type 3 data | ||
df_type_3 = read_excel_file(CBS_TYPE_3_SUMMARY_FILE, 5, df_type_3_columns) | ||
if df_type_3.empty: | ||
return df_type_1_total | ||
df_type_3["provider_code"] = 3 | ||
df_type_3["road_segment_name_cbs"] = df_type_3["from"] + "_" + df_type_3["to"] | ||
df_type_3_total = df_type_3[["road_segment_name_cbs", "road" , "segment", "provider_code", "2020_total","2021_total", "2022_total"]].copy() | ||
df_type_3_total.columns = ["road_segment_name_cbs", "road" , "segment", "provider_code", "2020_cbs", "2021_cbs", "2022_cbs"] | ||
df_type_3_total[["2020_cbs", "2021_cbs", "2022_cbs"]] = df_type_3_total[["2020_cbs", "2021_cbs", "2022_cbs"]].fillna(0) | ||
df_type_3["road_segment_name_cbs"] = df_type_3["from"].str.slice(start=1) + " - " + df_type_3["to"].str.slice(start=2) | ||
df_type_3_total = df_type_3[["road_segment_name_cbs", "road", "segment", "provider_code", "2020_total", "2021_total", "2022_total"]].copy() | ||
df_type_3_total.columns = ["road_segment_name_cbs", "road", "segment", "provider_code", "2020_cbs", "2021_cbs", "2022_cbs"] | ||
df_type_3_total.fillna({"2020_cbs": 0, "2021_cbs": 0, "2022_cbs": 0}, inplace=True) | ||
|
||
# Combine type 1 and type 3 data | ||
df_cbs_total = pd.concat([df_type_1_total, df_type_3_total]) | ||
df_cbs_total.set_index(["road" , "segment", "provider_code"], inplace=True) | ||
return df_cbs_total, df_type_1_2022 | ||
df_cbs_total.set_index(["road", "segment", "provider_code"], inplace=True) | ||
return df_cbs_total | ||
|
||
|
||
def get_anyway_count(): | ||
dfs = [] | ||
for road_segment in tqdm(RoadSegments.query.all()): | ||
|
||
road_segments = RoadSegments.query.all() | ||
for road_segment in tqdm(road_segments, desc="Processing road segments"): | ||
road_segment_id = road_segment.segment_id | ||
if road_segment_id != 97790010: | ||
continue | ||
road = road_segment.road | ||
segment = road_segment.segment | ||
road_segment_name = road_segment.from_name + ' - ' + road_segment.to_name | ||
print(road_segment_name) | ||
road_segment_name = f"{road_segment.from_name} - {road_segment.to_name}" | ||
ROAD_SEGMENTS_DICT[road_segment_id] = road_segment_name | ||
filters={"road_segment_id": road_segment_id, | ||
"accident_year": [2019, 2020,2021,2022, 2023]} | ||
|
||
filters = { | ||
"road_segment_id": road_segment_id, | ||
"accident_year": [2020, 2021, 2022] | ||
} | ||
query = db.session.query(AccidentMarkerView) | ||
location_fields, other_fields = split_location_fields_and_others(filters) | ||
|
||
if other_fields: | ||
query = query.filter(get_expression_for_fields(other_fields, AccidentMarkerView, and_)) | ||
query = query.filter( | ||
get_expression_for_road_segment_location_fields(location_fields, AccidentMarkerView) | ||
) | ||
test_query = query | ||
test_query = test_query.group_by(AccidentMarkerView.location_accuracy_hebrew) | ||
test_query = test_query.group_by(AccidentMarkerView.location_accuracy_hebrew, AccidentMarkerView.provider_code, AccidentMarkerView.accident_year) | ||
test_query = test_query.with_entities( | ||
AccidentMarkerView.provider_code, | ||
AccidentMarkerView.location_accuracy_hebrew, | ||
AccidentMarkerView.accident_year, | ||
func.count(AccidentMarkerView.location_accuracy_hebrew)) | ||
|
||
df2 = pd.read_sql_query(test_query.statement, test_query.session.bind) | ||
print(df2) | ||
query = query.group_by(AccidentMarkerView.provider_code, | ||
AccidentMarkerView.accident_severity, | ||
AccidentMarkerView.accident_year) | ||
query = query.filter(get_expression_for_fields(other_fields, AccidentMarkerView)) | ||
if location_fields: | ||
query = query.filter(get_expression_for_road_segment_location_fields(location_fields, AccidentMarkerView)) | ||
|
||
query = query.group_by(AccidentMarkerView.provider_code, AccidentMarkerView.accident_year) | ||
query = query.with_entities( | ||
AccidentMarkerView.provider_code, | ||
AccidentMarkerView.accident_severity, | ||
AccidentMarkerView.accident_year, | ||
func.count(AccidentMarkerView.accident_severity), | ||
func.count().label("anyway_count"), | ||
) | ||
|
||
|
||
|
||
df = pd.read_sql_query(query.statement, query.session.bind) | ||
df.rename(columns={"count_1": "anyway_count"}, inplace=True) # pylint: disable=no-member | ||
df["road_segment_id"] = road_segment_id | ||
df["road"] = road | ||
df["segment"] = segment | ||
df["road_segment_name"] = road_segment_name | ||
dfs.append(df) | ||
|
||
df_alls_segments = pd.concat(dfs) | ||
df_alls_segments.sort_values(['road_segment_id', 'provider_code', 'accident_year'], inplace=True) | ||
return df_alls_segments | ||
df_all_segments = pd.concat(dfs) | ||
df_all_segments.sort_values(["road_segment_id", "provider_code", "accident_year"], inplace=True) | ||
return df_all_segments | ||
|
||
|
||
def parse(): | ||
df_anyway = get_anyway_count() | ||
df_anyway["road_segment_id"] = df_anyway["road_segment_id"].astype(int) | ||
df_anyway_total = df_anyway.groupby(["road", "segment" ,"provider_code", "road_segment_id", "accident_year"])["anyway_count"].sum() | ||
df_anyway_total = df_anyway_total.unstack(-1) | ||
df_anyway_total.fillna(0, inplace=True) | ||
df_cbs_total, df_type_1_2022 = get_cbs_count() | ||
df_anyway_total.reset_index(inplace=True) | ||
df_anyway_total.set_index(["road" , "segment", "provider_code"], inplace=True) | ||
df_anyway_total = df_anyway.groupby(["road", "segment", "provider_code", "road_segment_id", "accident_year"])["anyway_count"].sum().unstack(fill_value=0).reset_index() | ||
df_anyway_total.set_index(["road", "segment", "provider_code"], inplace=True) | ||
|
||
df_cbs_total = get_cbs_count() | ||
if df_cbs_total.empty: | ||
return | ||
|
||
df_total = pd.merge(df_cbs_total, df_anyway_total, left_index=True, right_index=True, how="outer") | ||
df_total.reset_index(inplace=True) | ||
df_total["road_segment_name"] = df_total.road_segment_id.apply(lambda s: ROAD_SEGMENTS_DICT.get(s)) | ||
df_total = df_total.rename(columns = {2020: "2020_anyway", 2021: "2021_anyway", 2022: "2022_anyway"}) | ||
df_total = df_total[["road_segment_name_cbs", "road_segment_name", "road_segment_id", "road", "segment", "provider_code", "2020_cbs", "2020_anyway", "2021_cbs", "2021_anyway", "2022_cbs", "2022_anyway"]] | ||
df_total["2020_mismatch"] = df_total["2020_cbs"] != df_total["2020_anyway"] | ||
df_total["2021_mismatch"] = df_total["2021_cbs"] != df_total["2021_anyway"] | ||
df_total["2022_mismatch"] = df_total["2022_cbs"] != df_total["2022_anyway"] | ||
df_total["any_mismatch"] = df_total[["2020_mismatch", | ||
"2021_mismatch", | ||
"2022_mismatch"]].any(axis=1) | ||
df_total.to_csv("cbs_anyway_road_segments.csv", index=False) | ||
df_total["road_segment_name"] = df_total["road_segment_id"].map(ROAD_SEGMENTS_DICT) | ||
df_total.rename(columns={2020: "2020_anyway", 2021: "2021_anyway", 2022: "2022_anyway"}, inplace=True) | ||
df_total = df_total[[ | ||
"road_segment_name_cbs", "road_segment_name", "road_segment_id", "road", "segment", "provider_code", | ||
"2020_cbs", "2020_anyway", "2021_cbs", "2021_anyway", "2022_cbs", "2022_anyway" | ||
]] | ||
df_total["road_segment_name_cbs"] = df_total["road_segment_name_cbs"].str.strip() | ||
df_total["road_segment_name_cbs"] = df_total["road_segment_name_cbs"].replace(r'\s+', ' ', regex=True) | ||
df_total["road_names_matches"] = df_total["road_segment_name_cbs"] == df_total["road_segment_name"] | ||
df_total["2020_match"] = df_total["2020_cbs"] == df_total["2020_anyway"] | ||
df_total["2021_match"] = df_total["2021_cbs"] == df_total["2021_anyway"] | ||
df_total["2022_match"] = df_total["2022_cbs"] == df_total["2022_anyway"] | ||
df_total["all_match"] = df_total[["2020_match", "2021_match", "2022_match"]].all(axis=1) | ||
df_total["diff_anyway_cbs"] = df_total[["2020_anyway", "2021_anyway", "2022_anyway"]].sum(axis=1) - df_total[["2020_cbs", "2021_cbs", "2022_cbs"]].sum(axis=1) | ||
|
||
os.makedirs(OUTPUT_DIR, exist_ok=True) | ||
df_total.to_csv(OUTPUT_FILE, index=False) | ||
print(f"Output saved to {OUTPUT_FILE}") |
File renamed without changes.
File renamed without changes.
File renamed without changes.