我正在创建的程序旨在在几个邮政编码中创建几个点，并找到从这些点中的每一个到感兴趣的邮政编码 5 英里范围内的每个邮政编码中的每个点的距离。这是通过利用谷歌地图距离矩阵服务并捕获距离数据来完成的。我创建了一个冗长的函数来做几件事（我认为它需要进一步分解）。这就是我认为问题所在。
一切正常，但是，当我使用 Pyinstaller 创建可执行文件时，我在首次加载和尝试运行程序的主要功能时收到了几个错误。这些错误似乎集中在 pyproj 和 geopandas 上。
我在其他几个地方看到过这个问题。我无法成功应用在这些地方讨论的解决方案。提出的解决方案包括：
将 pyproj 降级到 1.9.6 - 请参阅下面的错误
在 pyinstaller 中添加一个钩子文件 - 目录中已经有一个钩子文件
在创建的规范文件的隐藏导入部分中包含 pyproj._datadir 和 pyproj.datadir。
使用 os.environ['PROJ_LIB'] 并将其设置为“/share”中的共享文件夹
我正在使用的软件包：
import pandas as pd
import tkinter as tk
import tkinter.filedialog
import os
import geopandas as gpd
from shapely.geometry import Point,LineString
import shapely.wkt
import googlemaps
from googlemaps.exceptions import ApiError
import datetime
from statistics import median
import _thread
规格文件：
# -*- mode: python -*-
block_cipher = None
a = Analysis(['main.py'],
pathex=['C:\\Users\\Keagan\\PycharmProjects\\upwork_jobs\\pet_sitting2\\gui'],
binaries=[],
datas=[],
hiddenimports=['fiona._shim','fiona.schema','pyproj._datadir','pyproj.datadir'],
hookspath=[],
runtime_hooks=[],
excludes=[],
win_no_prefer_redirects=False,
win_private_assemblies=False,
cipher=block_cipher,
noarchive=False)
pyz = PYZ(a.pure, a.zipped_data,
cipher=block_cipher)
exe = EXE(pyz,
a.scripts,
[],
exclude_binaries=True,
name='main',
debug=False,
bootloader_ignore_signals=False,
strip=False,
upx=True,
console=True )
coll = COLLECT(exe,
a.binaries,
a.zipfiles,
a.datas,
strip=False,
upx=True,
name='main')
主功能：
def model_distances(self, reference_names_list, reference_zips_df,zips_and_points_gdf,api_key):
gmaps = googlemaps.Client(api_key)
def find_key_value_connection(poi, to_location, list_of_dicts):
for item in list_of_dicts:
if poi == item["poi"] and to_location == item["to_location"] or to_location == item[
"poi"] and poi == \
item["to_location"]:
return True
return False
def projection(origin_projection, to_projection, geometry_object):
project = partial(
pyproj.transform,
pyproj.Proj(init=origin_projection),
pyproj.Proj(init=to_projection)
)
return transform(project, geometry_object)
zip_code_intersect_list = []
completed_locations_dict = {}
completed_locations_list = []
count = 0
google_credit_count = 0
completed_locations_df = None
buffer_list = []
for name in reference_names_list:
print("we are on: {}".format(name))
if os.path.isfile("output_files/completed_locations_{}.xlsx".format(name)) and completed_locations_df is None:
print("found backup, opening it")
completed_locations_df = pd.read_excel("output_files/completed_locations_{}.xlsx".format(name))
for item in completed_locations_df.itertuples():
completed_locations_dict["poi"] = int(item.poi)
completed_locations_dict["to_location"] = int(item.to_location)
completed_locations_dict["poi_zip"] = item.poi_zip
completed_locations_dict["to_zip"] = item.to_zip
completed_locations_dict["poi_name"] = item.poi_name
completed_locations_dict["to_name"] = item.to_name
completed_locations_dict["id"] = item.id
completed_locations_dict["distance"] = float(item.distance)
completed_locations_dict["time"] = float(item.time)
completed_locations_list.append(completed_locations_dict.copy())
elif not os.path.isfile("output_files/completed_locations_{}.xlsx".format(name)):
print("creating a backup")
completed_locations_df = pd.DataFrame()
completed_locations_df.to_excel("completed_locations_{}.xlsx".format(name))
for zip in reference_zips_df.itertuples():
if zip.name == name:
print("we are in zipcode: {}".format(zip.zip))
for poi in zips_and_points_gdf.itertuples():
if str(poi.zip_left) == str(zip.zip):
buffer = ""
poi_zip = ""
if poi_zip == None or poi.zip_left != poi_zip:
poi_zip = poi.zip_left
buffer = shapely.wkt.loads(poi.zip_center_point).buffer(8046)
buffer_list.append(buffer)
for to_location in zips_and_points_gdf.itertuples():
if poi.zip_left != to_location.zip_left and to_location.geometry.intersects(
buffer) and to_location.zip_left not in zip_code_intersect_list:
zip_code_intersect_list.append(to_location.zip_left)
for to_location in zips_and_points_gdf.itertuples():
if to_location.zip_left in zip_code_intersect_list and to_location.name_left == name:
if find_key_value_connection(int(poi.Index), int(to_location.Index),
completed_locations_list):
print(
"point at index {} was already calculated to point at index {}, google credit at: {}".format(
poi.Index, to_location.Index, google_credit_count))
else:
google_credit_count += 1
count += 1
print(
"calculating point at index {} to index {}, google credit at: {}".format(
poi.Index, to_location.Index, google_credit_count))
new_poi = projection("epsg:26910", "epsg:4326", poi.geometry)
new_to_location = projection("epsg:26910", "epsg:4326", to_location.geometry)
result = gmaps.distance_matrix((new_poi.y, new_poi.x),
(new_to_location.y,new_to_location.x))
completed_locations_dict["poi"] = int(poi.Index)
completed_locations_dict["to_location"] = int(to_location.Index)
completed_locations_dict["poi_zip"] = poi.zip_left
completed_locations_dict["to_zip"] = to_location.zip_left
completed_locations_dict["poi_name"] = zip.name
completed_locations_dict["to_name"] = to_location.name_left
completed_locations_dict["id"] = str(poi.zip_left) + str(
poi.Index) + "-" + str(to_location.zip_left) + str(to_location.Index)
try:
completed_locations_dict["time"] = \
result["rows"][0]["elements"][0]["duration"]["value"] / 60
completed_locations_dict["distance"] = \
result["rows"][0]["elements"][0]["distance"]["value"] / 1609.3
except KeyError:
completed_locations_dict["time"] = "nan"
completed_locations_dict["distance"] = "nan"
completed_locations_list.append(completed_locations_dict.copy())
if count > 500:
print("backup exists appending new df to backup")
completed_locations_df = pd.DataFrame(completed_locations_list)
completed_locations_df.to_excel("output_files/completed_locations_{}.xlsx".format(name))
count = 0
if google_credit_count >= 10000:
continue_program = input(
"desired google credit has hit $50, continue or change keys?(continue/change/quit): ")
while continue_program != "continue":
if continue_program == "quit":
# with open("backup_save.json", "w") as backup_file:
# json.dump(completed_locations_list.copy(), backup_file)
completed_locations_df = pd.DataFrame(completed_locations_list)
completed_locations_df.to_excel("output_files/completed_locations_{}.xlsx".format(name))
print("saving to excel")
quit()
new_key = input("please insert a new key: ")
gmaps = googlemaps.Client(key=new_key)
try:
# res = gmaps.geocode("Austin, Texas")
continue_program = input("valid key, continue? (continue/quit): ")
except (ValueError, ApiError):
new_key = input("invalid key, try again: ")
google_credit_count = 0
zip_code_intersect_list = []
completed_locations_df = pd.DataFrame(completed_locations_list)
return completed_locations_df
尝试将 pyproj 降级到 1.9.6 时：
UnsatisfiableError: The following specifications were found to be incompatible with each other:
首次启动工具时：
Warning:
The MATPLOTLIBDATA environment variable was deprecated in Matplotlib 3.1 and will be removed in 3.3.
exec(bytecode, module.__dict__)
Traceback (most recent call last):
File "site-packages\pyproj\datadir.py", line 101, in get_data_dir
pyproj.exceptions.DataDirError: Valid PROJ data directory not found.Either set the path using the environmental variable PROJ_LIB or with `pyproj.datadir.set_data_dir`.
Exception ignored in: 'pyproj._datadir.get_pyproj_context'
Traceback (most recent call last):
File "site-packages\pyproj\datadir.py", line 101, in get_data_dir
pyproj.exceptions.DataDirError: Valid PROJ data directory not found.Either set the path using the environmental variable PROJ_LIB or with `pyproj.datadir.set_data_dir`.
proj_create: Cannot find proj.db
proj_create: init=epsg:/init=IGNF: syntax not supported in non-PROJ4 emulation mode
Invalid projection: +init=epsg:4326 +type=crs
运行工具时：
<code that runs fine before>
Traceback (most recent call last):
File "site-packages\pyproj\datadir.py", line 101, in get_data_dir
pyproj.exceptions.DataDirError: Valid PROJ data directory not found.Either set the path using the environmental variable PROJ_LIB or with `pyproj.datadir.set_data_dir`.
Exception ignored in: 'pyproj._datadir.get_pyproj_context'
Traceback (most recent call last):
File "site-packages\pyproj\datadir.py", line 101, in get_data_dir
pyproj.exceptions.DataDirError: Valid PROJ data directory not found.Either set the path using the environmental variable PROJ_LIB or with `pyproj.datadir.set_data_dir`.
proj_create: Cannot find proj.db
proj_create: init=epsg:/init=IGNF: syntax not supported in non-PROJ4 emulation mode
Unhandled exception in thread started by <bound method ZipAnalysisGUI.analyze_data of <__main__.ZipAnalysisGUI object at 0x000001DAAD51A668>>
Traceback (most recent call last):
File "main.py", line 480, in analyze_data
File "main.py", line 237, in model_distances
File "main.py", line 157, in projection
File "site-packages\pyproj\proj.py", line 147, in __init__
File "site-packages\pyproj\crs.py", line 391, in from_user_input
File "site-packages\pyproj\crs.py", line 260, in __init__
File "pyproj/_crs.pyx", line 1292, in pyproj._crs._CRS.__init__
pyproj.exceptions.CRSError: Invalid projection: +init=epsg:26910 +type=crs
根据上面的错误，我认为它正在被赶上：
def projection(origin_projection, to_projection, geometry_object):
project = partial(
pyproj.transform,
pyproj.Proj(init=origin_projection),
pyproj.Proj(init=to_projection)
)
return transform(project, geometry_object)
从 pycharm 运行时，这一切都运行良好。一旦我尝试将它作为可执行文件运行，它就会开始崩溃。我相当肯定它弄乱了上述功能，但我无法确定原因。如果需要，我可以共享更多代码或整个文件。