mobisurvstd 0.3.0__tar.gz → 0.5.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (87) hide show
  1. {mobisurvstd-0.3.0/src/mobisurvstd.egg-info → mobisurvstd-0.5.0}/PKG-INFO +11 -2
  2. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/README.md +10 -1
  3. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/pyproject.toml +1 -1
  4. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/clean.py +4 -4
  5. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/cli.py +1 -1
  6. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/common/cars.py +1 -1
  7. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/common/persons.py +1 -1
  8. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/common/trips.py +1 -1
  9. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edgt/survey.py +65 -58
  10. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edvm/survey.py +46 -39
  11. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edvm/trajets.py +1 -1
  12. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edvm/zones.py +2 -2
  13. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2010/survey.py +10 -7
  14. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2010/trajets.py +1 -1
  15. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2020/survey.py +1 -1
  16. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2020/trajets.py +5 -5
  17. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emc2/survey.py +60 -51
  18. mobisurvstd-0.5.0/src/mobisurvstd/emd/common.py +42 -0
  19. mobisurvstd-0.5.0/src/mobisurvstd/emd/deplacements.py +160 -0
  20. mobisurvstd-0.5.0/src/mobisurvstd/emd/menages.py +355 -0
  21. mobisurvstd-0.5.0/src/mobisurvstd/emd/personnes.py +312 -0
  22. mobisurvstd-0.5.0/src/mobisurvstd/emd/survey.py +283 -0
  23. mobisurvstd-0.5.0/src/mobisurvstd/emd/trajets.py +271 -0
  24. mobisurvstd-0.5.0/src/mobisurvstd/emd/zones.py +222 -0
  25. mobisurvstd-0.5.0/src/mobisurvstd/emp/__init__.py +1 -0
  26. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emp/survey.py +1 -1
  27. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/main.py +46 -17
  28. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/resources/admin_express.py +1 -1
  29. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/utils.py +1 -4
  30. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0/src/mobisurvstd.egg-info}/PKG-INFO +11 -2
  31. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd.egg-info/SOURCES.txt +8 -0
  32. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/LICENSE.md +0 -0
  33. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/setup.cfg +0 -0
  34. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/__init__.py +0 -0
  35. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/__main__.py +0 -0
  36. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/classes.py +0 -0
  37. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/common/__init__.py +0 -0
  38. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/common/clean.py +0 -0
  39. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/common/households.py +0 -0
  40. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/common/legs.py +0 -0
  41. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/common/modes.py +0 -0
  42. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/common/motorcycles.py +0 -0
  43. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/common/zones.py +0 -0
  44. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edgt/__init__.py +0 -0
  45. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edgt/common.py +0 -0
  46. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edgt/deplacements.py +0 -0
  47. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edgt/menages.py +0 -0
  48. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edgt/personnes.py +0 -0
  49. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edgt/trajets.py +0 -0
  50. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edgt/zones.py +0 -0
  51. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edvm/__init__.py +0 -0
  52. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edvm/common.py +0 -0
  53. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edvm/deplacements.py +0 -0
  54. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edvm/menages.py +0 -0
  55. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/edvm/personnes.py +0 -0
  56. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2010/__init__.py +0 -0
  57. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2010/deplacements.py +0 -0
  58. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2010/menages.py +0 -0
  59. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2010/personnes.py +0 -0
  60. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2010/zones.py +0 -0
  61. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2020/__init__.py +0 -0
  62. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2020/deplacements.py +0 -0
  63. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2020/menages.py +0 -0
  64. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2020/motos.py +0 -0
  65. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2020/personnes.py +0 -0
  66. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/egt2020/voitures.py +0 -0
  67. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emc2/__init__.py +0 -0
  68. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emc2/common.py +0 -0
  69. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emc2/deplacements.py +0 -0
  70. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emc2/menages.py +0 -0
  71. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emc2/personnes.py +0 -0
  72. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emc2/trajets.py +0 -0
  73. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emc2/zones.py +0 -0
  74. {mobisurvstd-0.3.0/src/mobisurvstd/emp → mobisurvstd-0.5.0/src/mobisurvstd/emd}/__init__.py +0 -0
  75. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emp/deplacements.py +0 -0
  76. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emp/menages.py +0 -0
  77. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emp/motos.py +0 -0
  78. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emp/personnes.py +0 -0
  79. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/emp/voitures.py +0 -0
  80. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/logger.py +0 -0
  81. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/resources/__init__.py +0 -0
  82. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/resources/insee_data.py +0 -0
  83. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/resources/nuts.py +0 -0
  84. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd/schema.py +0 -0
  85. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd.egg-info/dependency_links.txt +0 -0
  86. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd.egg-info/requires.txt +0 -0
  87. {mobisurvstd-0.3.0 → mobisurvstd-0.5.0}/src/mobisurvstd.egg-info/top_level.txt +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: mobisurvstd
3
- Version: 0.3.0
3
+ Version: 0.5.0
4
4
  Summary: A tool to standardize French mobility survey datasets (EMC2, EGT, EMP, etc.) into a unified format.
5
5
  Author-email: Lucas Javaudin <lucas@lucasjavaudin.com>
6
6
  License-Expression: MIT
@@ -78,6 +78,7 @@ Also surveys based on previous formats are still in use today:
78
78
  (until 2018);
79
79
  - **EDGT** (Enquêtes Déplacements Grands Territoires, CEREMA): mobility surveys for periphery areas
80
80
  (until 2018);
81
+ - **EMD** (Enquêtes Ménages Déplacements, CEREMA): other mobility surveys from CEREMA (until 2018);
81
82
  - [**EGT 2010**](https://omnil.fr/egt-2010) (Enquête Globale Transport, Île-de-France Mobilités):
82
83
  previous version of the Île-de-France mobility survey;
83
84
  - [**ENTD**](https://www.statistiques.developpement-durable.gouv.fr/enquete-nationale-transports-et-deplacements-entd-2008)
@@ -149,11 +150,18 @@ mobisurvstd.standardize(
149
150
 
150
151
  For more, check the [User Guide](https://mobisurvstd.github.io/MobiSurvStd/howto.html).
151
152
 
153
+ **Citing MobiSurvStd**
154
+
155
+ If you use MobiSurvStd in a publication or project, please include the following attribution:
156
+ "This work used the MobiSurvStd library developed by Lucas Javaudin, available at
157
+ [https://github.com/MobiSurvStd/MobiSurvStd]()".
158
+
152
159
  ---
153
160
 
154
161
  ## Case Study: Bicycle Use
155
162
 
156
- The following graph represents the share of bicycle trips for EMC², EDGT, EDVM, and EGT surveys.
163
+ The following graph represents the share of bicycle trips for EMC², EDGT, EDVM, EMD, and EGT
164
+ surveys.
157
165
  The circle colors represent the average number of bicycles in the surveyed households.
158
166
  The circle sizes represent the expected number of trips in the surveyed area.
159
167
 
@@ -182,6 +190,7 @@ Currently, MobiSurvStd supports the following survey types:
182
190
  - `egt2010`
183
191
  - `edgt`
184
192
  - `edvm`
193
+ - `emd`
185
194
 
186
195
  See [Survey Types](https://mobisurvstd.github.io/MobiSurvStd/surveys.html) for more.
187
196
 
@@ -46,6 +46,7 @@ Also surveys based on previous formats are still in use today:
46
46
  (until 2018);
47
47
  - **EDGT** (Enquêtes Déplacements Grands Territoires, CEREMA): mobility surveys for periphery areas
48
48
  (until 2018);
49
+ - **EMD** (Enquêtes Ménages Déplacements, CEREMA): other mobility surveys from CEREMA (until 2018);
49
50
  - [**EGT 2010**](https://omnil.fr/egt-2010) (Enquête Globale Transport, Île-de-France Mobilités):
50
51
  previous version of the Île-de-France mobility survey;
51
52
  - [**ENTD**](https://www.statistiques.developpement-durable.gouv.fr/enquete-nationale-transports-et-deplacements-entd-2008)
@@ -117,11 +118,18 @@ mobisurvstd.standardize(
117
118
 
118
119
  For more, check the [User Guide](https://mobisurvstd.github.io/MobiSurvStd/howto.html).
119
120
 
121
+ **Citing MobiSurvStd**
122
+
123
+ If you use MobiSurvStd in a publication or project, please include the following attribution:
124
+ "This work used the MobiSurvStd library developed by Lucas Javaudin, available at
125
+ [https://github.com/MobiSurvStd/MobiSurvStd]()".
126
+
120
127
  ---
121
128
 
122
129
  ## Case Study: Bicycle Use
123
130
 
124
- The following graph represents the share of bicycle trips for EMC², EDGT, EDVM, and EGT surveys.
131
+ The following graph represents the share of bicycle trips for EMC², EDGT, EDVM, EMD, and EGT
132
+ surveys.
125
133
  The circle colors represent the average number of bicycles in the surveyed households.
126
134
  The circle sizes represent the expected number of trips in the surveyed area.
127
135
 
@@ -150,6 +158,7 @@ Currently, MobiSurvStd supports the following survey types:
150
158
  - `egt2010`
151
159
  - `edgt`
152
160
  - `edvm`
161
+ - `emd`
153
162
 
154
163
  See [Survey Types](https://mobisurvstd.github.io/MobiSurvStd/surveys.html) for more.
155
164
 
@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
6
6
 
7
7
  [project]
8
8
  name = "mobisurvstd"
9
- version = "0.3.0"
9
+ version = "0.5.0"
10
10
  description = "A tool to standardize French mobility survey datasets (EMC2, EGT, EMP, etc.) into a unified format."
11
11
  readme = "README.md"
12
12
  authors = [{ name = "Lucas Javaudin", email = "lucas@lucasjavaudin.com" }]
@@ -1017,7 +1017,7 @@ def clean(
1017
1017
  ), "`origin_purpose` is education-related for a non-student person"
1018
1018
  assert trips.select(
1019
1019
  (
1020
- pl.col("origin_purpose").cast(pl.String).str.extract("(\w+):?")
1020
+ pl.col("origin_purpose").cast(pl.String).str.extract(r"(\w+):?")
1021
1021
  == pl.col("origin_purpose_group")
1022
1022
  ).all()
1023
1023
  ).item(), "Columns `origin_purpose` and `origin_purpose_group` have some inconsistencies"
@@ -1043,7 +1043,7 @@ def clean(
1043
1043
  ), "`destination_purpose` is education-related for a non-student person"
1044
1044
  assert trips.select(
1045
1045
  (
1046
- pl.col("destination_purpose").cast(pl.String).str.extract("(\w+):?")
1046
+ pl.col("destination_purpose").cast(pl.String).str.extract(r"(\w+):?")
1047
1047
  == pl.col("destination_purpose_group")
1048
1048
  ).all()
1049
1049
  ).item(), (
@@ -1078,7 +1078,7 @@ def clean(
1078
1078
  )
1079
1079
  assert trips.select(
1080
1080
  (
1081
- pl.col("origin_escort_purpose").cast(pl.String).str.extract("(\w+):?")
1081
+ pl.col("origin_escort_purpose").cast(pl.String).str.extract(r"(\w+):?")
1082
1082
  == pl.col("origin_escort_purpose_group")
1083
1083
  ).all()
1084
1084
  ).item(), (
@@ -1101,7 +1101,7 @@ def clean(
1101
1101
  )
1102
1102
  assert trips.select(
1103
1103
  (
1104
- pl.col("destination_escort_purpose").cast(pl.String).str.extract("(\w+):?")
1104
+ pl.col("destination_escort_purpose").cast(pl.String).str.extract(r"(\w+):?")
1105
1105
  == pl.col("destination_escort_purpose_group")
1106
1106
  ).all()
1107
1107
  ).item(), (
@@ -20,7 +20,7 @@ def standardizer(
20
20
  survey_type: Annotated[
21
21
  str | None,
22
22
  typer.Option(
23
- help="Format of the original survey. Possible values: `emc2`, `emp2019`, `egt2010`, `egt2020`, `edgt`, `edvm`."
23
+ help="Format of the original survey. Possible values: `emc2`, `emp2019`, `egt2010`, `egt2020`, `edgt`, `edvm`, `emd`."
24
24
  ),
25
25
  ] = None,
26
26
  bulk: Annotated[
@@ -36,7 +36,7 @@ def indexing(lf: pl.LazyFrame, existing_cols: list[str]):
36
36
  def add_fuel_type_group(lf: pl.LazyFrame, existing_cols: list[str]):
37
37
  if "fuel_type" in existing_cols:
38
38
  lf = lf.with_columns(
39
- fuel_type_group=pl.col("fuel_type").cast(pl.String).str.extract("(\w+):?")
39
+ fuel_type_group=pl.col("fuel_type").cast(pl.String).str.extract(r"(\w+):?")
40
40
  )
41
41
  existing_cols.append("fuel_type_group")
42
42
  return lf
@@ -98,7 +98,7 @@ def add_professional_occupation(lf: pl.LazyFrame, existing_cols: list[str]):
98
98
  ):
99
99
  lf = lf.with_columns(
100
100
  professional_occupation=pl.col("detailed_professional_occupation").str.extract(
101
- "(\w+):?"
101
+ r"(\w+):?"
102
102
  )
103
103
  )
104
104
  existing_cols.append("professional_occupation")
@@ -108,7 +108,7 @@ def add_purpose_groups(lf: pl.LazyFrame, existing_cols: list[str]):
108
108
  if col in existing_cols:
109
109
  group_col = f"{col}_group"
110
110
  lf = lf.with_columns(
111
- pl.col(col).cast(pl.String).str.extract("(\w+):?").alias(group_col)
111
+ pl.col(col).cast(pl.String).str.extract(r"(\w+):?").alias(group_col)
112
112
  )
113
113
  return lf
114
114
 
@@ -23,59 +23,15 @@ from .trajets import standardize_legs
23
23
  from .zones import read_detailed_zones, read_draw_zones, read_special_locations
24
24
 
25
25
 
26
- def standardize(source: str | ZipFile):
26
+ def standardize(source: str | ZipFile, skip_spatial: bool = False):
27
27
  source_name = source.filename if isinstance(source, ZipFile) else source
28
28
  logger.info(f"Standardizing EDGT survey from `{source_name}`")
29
- # Special locations.
30
- filename = special_locations_filename(source)
31
- if filename is None:
32
- special_locations = None
33
- elif "EDGT_SCOTAM_2017" in source_name or "Angers12" in source_name or "EDGTFVG2016":
34
- # Note. Special case for Metz 2017 and Angers 2012: I cannot figure out the ids in the GT
35
- # and ZF files.
36
- # For Annemasse 2016, the GT id does not seem to be specified.
37
- logger.warning("Cannot read special locations: ids are invalid")
29
+ if skip_spatial:
38
30
  special_locations = None
39
- else:
40
- logger.debug(f"Reading special locations from `{filename}`")
41
- special_locations = read_special_locations(filename)
42
- # Detailed zones.
43
- filename = detailed_zones_filename(source)
44
- if filename is None:
45
- logger.debug(f"No file with detailed zones in `{source_name}`")
46
- detailed_zones = None
47
- elif "EDGT_SCOTAM_2017" in source_name or "Angers12" in source_name or "FaF_Zones_fines":
48
- # Note. Special case for Metz 2017 and Angers 2012: I cannot figure out the ids in the GT
49
- # and ZF files.
50
- # For Bayonne 2010, the ids are missing.
51
- logger.warning("Cannot read detailed zones: ids are invalid")
52
31
  detailed_zones = None
53
- else:
54
- logger.debug(f"Reading detailed zones from `{filename}`")
55
- detailed_zones = read_detailed_zones(filename)
56
- # Draw zones.
57
- filename = draw_zones_filename(source)
58
- if filename is None:
59
- logger.debug(f"No file with draw zones in `{source_name}`")
60
32
  draw_zones = None
61
33
  else:
62
- logger.debug(f"Reading draw zones from `{filename}`")
63
- draw_zones = read_draw_zones(filename)
64
-
65
- if special_locations is not None:
66
- # For the Angers 2022 survey, the ids in the detailed zones shapefile have 3 zeros removed
67
- # compared to the ids in the special locations shapefile.
68
- assert detailed_zones is not None, (
69
- "Special locations are defined but there is no data on detailed zones"
70
- )
71
- if "detailed_zone_id" not in special_locations.columns:
72
- special_locations = identify_detailed_zone_id(special_locations, detailed_zones)
73
- dz_gcd = np.gcd.reduce(detailed_zones["detailed_zone_id"].astype(int))
74
- sl_gcd = np.gcd.reduce(special_locations["detailed_zone_id"].astype(int))
75
- if dz_gcd < sl_gcd and np.log10(sl_gcd).is_integer():
76
- detailed_zones["detailed_zone_id"] = (
77
- detailed_zones["detailed_zone_id"].astype(int) * sl_gcd
78
- ).astype(str)
34
+ special_locations, detailed_zones, draw_zones = read_spatial_data(source, source_name)
79
35
 
80
36
  if special_locations is not None:
81
37
  special_locations_coords = get_coords(special_locations, "special_location")
@@ -180,6 +136,61 @@ def standardize(source: str | ZipFile):
180
136
  )
181
137
 
182
138
 
139
+ def read_spatial_data(source: str | ZipFile, source_name: str):
140
+ # Special locations.
141
+ filename = special_locations_filename(source)
142
+ if filename is None:
143
+ special_locations = None
144
+ elif "EDGT_SCOTAM_2017" in source_name or "Angers12" in source_name or "EDGTFVG2016":
145
+ # Note. Special case for Metz 2017 and Angers 2012: I cannot figure out the ids in the GT
146
+ # and ZF files.
147
+ # For Annemasse 2016, the GT id does not seem to be specified.
148
+ logger.warning("Cannot read special locations: ids are invalid")
149
+ special_locations = None
150
+ else:
151
+ logger.debug(f"Reading special locations from `{filename}`")
152
+ special_locations = read_special_locations(filename)
153
+ # Detailed zones.
154
+ filename = detailed_zones_filename(source)
155
+ if filename is None:
156
+ logger.debug(f"No file with detailed zones in `{source_name}`")
157
+ detailed_zones = None
158
+ elif "EDGT_SCOTAM_2017" in source_name or "Angers12" in source_name or "FaF_Zones_fines":
159
+ # Note. Special case for Metz 2017 and Angers 2012: I cannot figure out the ids in the GT
160
+ # and ZF files.
161
+ # For Bayonne 2010, the ids are missing.
162
+ logger.warning("Cannot read detailed zones: ids are invalid")
163
+ detailed_zones = None
164
+ else:
165
+ logger.debug(f"Reading detailed zones from `{filename}`")
166
+ detailed_zones = read_detailed_zones(filename)
167
+ # Draw zones.
168
+ filename = draw_zones_filename(source)
169
+ if filename is None:
170
+ logger.debug(f"No file with draw zones in `{source_name}`")
171
+ draw_zones = None
172
+ else:
173
+ logger.debug(f"Reading draw zones from `{filename}`")
174
+ draw_zones = read_draw_zones(filename)
175
+
176
+ if special_locations is not None:
177
+ # For the Angers 2022 survey, the ids in the detailed zones shapefile have 3 zeros removed
178
+ # compared to the ids in the special locations shapefile.
179
+ assert (
180
+ detailed_zones is not None
181
+ ), "Special locations are defined but there is no data on detailed zones"
182
+ if "detailed_zone_id" not in special_locations.columns:
183
+ special_locations = identify_detailed_zone_id(special_locations, detailed_zones)
184
+ dz_gcd = np.gcd.reduce(detailed_zones["detailed_zone_id"].astype(int))
185
+ sl_gcd = np.gcd.reduce(special_locations["detailed_zone_id"].astype(int))
186
+ if dz_gcd < sl_gcd and np.log10(sl_gcd).is_integer():
187
+ detailed_zones["detailed_zone_id"] = (
188
+ detailed_zones["detailed_zone_id"].astype(int) * sl_gcd
189
+ ).astype(str)
190
+
191
+ return special_locations, detailed_zones, draw_zones
192
+
193
+
183
194
  def survey_main_insee(source: str | bytes):
184
195
  return pl.scan_csv(source, separator=";").select("IDM4").first().collect().item()
185
196
 
@@ -215,7 +226,7 @@ def legs_filename(source: str | ZipFile):
215
226
  def detailed_zones_filename(source: str | ZipFile):
216
227
  return find_file(
217
228
  source,
218
- ".*_(ZF|Zones_Fines|Zones fines|ZInterne)(.*)?\.(TAB|shp|MIF)",
229
+ r".*_(ZF|Zones_Fines|Zones fines|ZInterne)(.*)?\.(TAB|shp|MIF)",
219
230
  subdir=os.path.join("Doc", "SIG"),
220
231
  as_url=True,
221
232
  )
@@ -228,7 +239,7 @@ def special_locations_filename(source: str | ZipFile):
228
239
  # locations for Lyon.)
229
240
  return find_file(
230
241
  source,
231
- "(?!.*ZF_GT).*(_GT|Gener)(.*)?\.(TAB|shp|MIF)",
242
+ r"(?!.*ZF_GT).*(_GT|Gener)(.*)?\.(TAB|shp|MIF)",
232
243
  subdir=os.path.join("Doc", "SIG"),
233
244
  as_url=True,
234
245
  )
@@ -236,7 +247,7 @@ def special_locations_filename(source: str | ZipFile):
236
247
 
237
248
  def draw_zones_filename(source: str | ZipFile):
238
249
  return find_file(
239
- source, ".*_DTIR(_.*)?\.(TAB|shp|MIF)", subdir=os.path.join("Doc", "SIG"), as_url=True
250
+ source, r".*_DTIR(_.*)?\.(TAB|shp|MIF)", subdir=os.path.join("Doc", "SIG"), as_url=True
240
251
  )
241
252
 
242
253
 
@@ -267,15 +278,13 @@ def fix_special_locations_with_gcd(
267
278
  pl.from_pandas(special_locations["detailed_zone_id"].astype(int)),
268
279
  default=None,
269
280
  )
270
- )
271
- .alias(f"{col}_detailed_zone"),
281
+ ).alias(f"{col}_detailed_zone"),
272
282
  # When the ZF is an actual ZF
273
283
  pl.when(mask)
274
284
  # Then the GT is null
275
285
  .then(pl.lit(None))
276
286
  # Otherwise use that GT as GT.
277
- .otherwise(f"{col}_detailed_zone")
278
- .alias(f"{col}_special_location"),
287
+ .otherwise(f"{col}_detailed_zone").alias(f"{col}_special_location"),
279
288
  )
280
289
  return df
281
290
 
@@ -298,15 +307,13 @@ def fix_special_locations(df: pl.LazyFrame, col: str, special_locations: gpd.Geo
298
307
  pl.from_pandas(special_locations["detailed_zone_id"].astype(int)),
299
308
  default=None,
300
309
  )
301
- )
302
- .alias(f"{col}_detailed_zone"),
310
+ ).alias(f"{col}_detailed_zone"),
303
311
  # When the ZF is an actual ZF
304
312
  pl.when(mask)
305
313
  # Then the GT is null
306
314
  .then(pl.lit(None))
307
315
  # Otherwise use that GT as GT.
308
- .otherwise(f"{col}_detailed_zone")
309
- .alias(f"{col}_special_location"),
316
+ .otherwise(f"{col}_detailed_zone").alias(f"{col}_special_location"),
310
317
  )
311
318
  return df
312
319
 
@@ -28,40 +28,15 @@ from .zones import (
28
28
  )
29
29
 
30
30
 
31
- def standardize(source: str | ZipFile):
31
+ def standardize(source: str | ZipFile, skip_spatial: bool = False):
32
32
  source_name = source.filename if isinstance(source, ZipFile) else source
33
33
  logger.info(f"Standardizing EDVM survey from `{source_name}`")
34
- if filename := special_locations_and_detailed_zones_filename(source):
35
- # Special case for Beauvais 2011.
36
- detailed_zones, special_locations = read_special_locations_and_detailed_zones(filename)
37
- else:
38
- # Special locations.
39
- if filename := special_locations_filename(source):
40
- logger.debug(f"Reading special locations from `{filename}`")
41
- special_locations = read_special_locations(filename)
42
- else:
43
- special_locations = None
44
- # Detailed zones.
45
- if filename := detailed_zones_filename(source):
46
- logger.debug(f"Reading detailed zones from `{filename}`")
47
- detailed_zones = read_detailed_zones(filename)
48
- else:
49
- logger.debug(f"No file with detailed zones in `{source_name}`")
50
- detailed_zones = None
51
- # Draw zones.
52
- if filename := draw_zones_filename(source):
53
- logger.debug(f"Reading draw zones from `{filename}`")
54
- draw_zones = read_draw_zones(filename)
55
- else:
56
- logger.debug(f"No file with draw zones in `{source_name}`")
34
+ if skip_spatial:
35
+ special_locations = None
36
+ detailed_zones = None
57
37
  draw_zones = None
58
-
59
- if special_locations is not None:
60
- assert detailed_zones is not None, (
61
- "Special locations are defined but there is no data on detailed zones"
62
- )
63
- if "detailed_zone_id" not in special_locations.columns:
64
- special_locations = identify_detailed_zone_id(special_locations, detailed_zones)
38
+ else:
39
+ special_locations, detailed_zones, draw_zones = read_spatial_data(source, source_name)
65
40
 
66
41
  if special_locations is not None:
67
42
  special_locations_coords = get_coords(special_locations, "special_location")
@@ -133,6 +108,42 @@ def standardize(source: str | ZipFile):
133
108
  )
134
109
 
135
110
 
111
+ def read_spatial_data(source: str | ZipFile, source_name: str):
112
+ if filename := special_locations_and_detailed_zones_filename(source):
113
+ # Special case for Beauvais 2011.
114
+ detailed_zones, special_locations = read_special_locations_and_detailed_zones(filename)
115
+ else:
116
+ # Special locations.
117
+ if filename := special_locations_filename(source):
118
+ logger.debug(f"Reading special locations from `{filename}`")
119
+ special_locations = read_special_locations(filename)
120
+ else:
121
+ special_locations = None
122
+ # Detailed zones.
123
+ if filename := detailed_zones_filename(source):
124
+ logger.debug(f"Reading detailed zones from `{filename}`")
125
+ detailed_zones = read_detailed_zones(filename)
126
+ else:
127
+ logger.debug(f"No file with detailed zones in `{source_name}`")
128
+ detailed_zones = None
129
+ # Draw zones.
130
+ if filename := draw_zones_filename(source):
131
+ logger.debug(f"Reading draw zones from `{filename}`")
132
+ draw_zones = read_draw_zones(filename)
133
+ else:
134
+ logger.debug(f"No file with draw zones in `{source_name}`")
135
+ draw_zones = None
136
+
137
+ if special_locations is not None:
138
+ assert (
139
+ detailed_zones is not None
140
+ ), "Special locations are defined but there is no data on detailed zones"
141
+ if "detailed_zone_id" not in special_locations.columns:
142
+ special_locations = identify_detailed_zone_id(special_locations, detailed_zones)
143
+
144
+ return special_locations, detailed_zones, draw_zones
145
+
146
+
136
147
  def survey_name(source: str | ZipFile):
137
148
  filename = find_file(source, ".*_std_men.csv", subdir="Csv", as_url=True)
138
149
  return re.match("(.*)_std_men.csv", os.path.basename(filename)).group(1)
@@ -212,15 +223,13 @@ def fix_special_locations_with_gcd(
212
223
  pl.from_pandas(special_locations["detailed_zone_id"].astype(int)),
213
224
  default=None,
214
225
  )
215
- )
216
- .alias(f"{col}_detailed_zone"),
226
+ ).alias(f"{col}_detailed_zone"),
217
227
  # When the ZF is an actual ZF
218
228
  pl.when(mask)
219
229
  # Then the GT is null
220
230
  .then(pl.lit(None))
221
231
  # Otherwise use that GT as GT.
222
- .otherwise(f"{col}_detailed_zone")
223
- .alias(f"{col}_special_location"),
232
+ .otherwise(f"{col}_detailed_zone").alias(f"{col}_special_location"),
224
233
  )
225
234
  return df
226
235
 
@@ -243,15 +252,13 @@ def fix_special_locations(df: pl.LazyFrame, col: str, special_locations: gpd.Geo
243
252
  pl.from_pandas(special_locations["detailed_zone_id"].astype(int)),
244
253
  default=None,
245
254
  )
246
- )
247
- .alias(f"{col}_detailed_zone"),
255
+ ).alias(f"{col}_detailed_zone"),
248
256
  # When the ZF is an actual ZF
249
257
  pl.when(mask)
250
258
  # Then the GT is null
251
259
  .then(pl.lit(None))
252
260
  # Otherwise use that GT as GT.
253
- .otherwise(f"{col}_detailed_zone")
254
- .alias(f"{col}_special_location"),
261
+ .otherwise(f"{col}_detailed_zone").alias(f"{col}_special_location"),
255
262
  )
256
263
  return df
257
264
 
@@ -124,7 +124,7 @@ def standardize_legs(
124
124
  )
125
125
  idx = ["ECH", "STT", "PER", "NDEP"]
126
126
 
127
- # For EMC², the walking legs are not recorded explicitly, instead, the walking time before and
127
+ # For EDVM, the walking legs are not recorded explicitly, instead, the walking time before and
128
128
  # after the legs are defined.
129
129
  # We create actual walking legs from these walking times.
130
130
 
@@ -122,14 +122,14 @@ def cast_id(s: gpd.GeoSeries):
122
122
  # "012345" -> "12345"
123
123
  # "123 456" -> "123456"
124
124
  # "123.456" -> "123456"
125
- # Altough it would be cleaner to keep the leading zero, it is safer to remove them because in
125
+ # Although it would be cleaner to keep the leading zero, it is safer to remove them because in
126
126
  # some cases there is not the same number of leading zeros in the zone files compared to the
127
127
  # survey's CSV files.
128
128
  return (
129
129
  s.astype(str)
130
130
  .str.replace(" ", "")
131
131
  .str.replace("[.]0$", "", n=1, regex=True)
132
- .str.replace("(?<=\d)[.](?=\d)", "", n=1, regex=True)
132
+ .str.replace(r"(?<=\d)[.](?=\d)", "", n=1, regex=True)
133
133
  .astype(int, errors="ignore")
134
134
  .astype(str)
135
135
  )
@@ -13,15 +13,18 @@ from .trajets import standardize_legs
13
13
  from .zones import read_detailed_zones
14
14
 
15
15
 
16
- def standardize(source: str | ZipFile):
16
+ def standardize(source: str | ZipFile, skip_spatial: bool = False):
17
17
  source_name = source.filename if isinstance(source, ZipFile) else source
18
18
  logger.info(f"Standardizing EGT2010 survey from `{source_name}`")
19
- # Detailed zones.
20
- filename = detailed_zones_filename(source)
21
- if filename is None:
22
- logger.error("Missing detailed zones file")
23
- return None
24
- detailed_zones = read_detailed_zones(filename)
19
+ if skip_spatial:
20
+ detailed_zones = None
21
+ else:
22
+ # Detailed zones.
23
+ filename = detailed_zones_filename(source)
24
+ if filename is None:
25
+ logger.error("Missing detailed zones file")
26
+ return None
27
+ detailed_zones = read_detailed_zones(filename)
25
28
  # Households.
26
29
  filename = households_filename(source)
27
30
  if filename is None:
@@ -155,7 +155,7 @@ def standardize_legs(
155
155
  trips: pl.LazyFrame,
156
156
  cars: pl.LazyFrame,
157
157
  motorcycles: pl.LazyFrame,
158
- detailed_zones: gpd.GeoDataFrame,
158
+ detailed_zones: gpd.GeoDataFrame | None,
159
159
  ):
160
160
  lf = scan_legs(filename)
161
161
  # Add household_id, person_id, and trip_id.
@@ -13,7 +13,7 @@ from .trajets import standardize_legs
13
13
  from .voitures import standardize_cars
14
14
 
15
15
 
16
- def standardize(source: str | ZipFile):
16
+ def standardize(source: str | ZipFile, skip_spatial: bool = False):
17
17
  source_name = source.filename if isinstance(source, ZipFile) else source
18
18
  logger.info(f"Standardizing EGT2020 survey from `{source_name}`")
19
19
  # Households.
@@ -236,10 +236,10 @@ def standardize_legs(
236
236
  lf = lf.with_columns(
237
237
  original_leg_id=pl.struct("IDCEREMA", "NP", "ND", "NT"),
238
238
  # The extract call is required because some modes are reported as "B616,skate", for example.
239
- mode=pl.col("MOYEN").str.extract("(\w+),?").replace_strict(MODE_MAP),
240
- car_type=pl.col("UVP").str.extract("(\w+),?").replace_strict(UVP_MAP),
239
+ mode=pl.col("MOYEN").str.extract(r"(\w+),?").replace_strict(MODE_MAP),
240
+ car_type=pl.col("UVP").str.extract(r"(\w+),?").replace_strict(UVP_MAP),
241
241
  car_index=pl.col("UVP")
242
- .str.extract("(\w+),?")
242
+ .str.extract(r"(\w+),?")
243
243
  .replace_strict(VEHICLE_INDEX_MAP, default=None),
244
244
  motorcycle_type=pl.col("U2RM").replace_strict(U2RM_MAP),
245
245
  motorcycle_index=pl.col("U2RM").replace_strict(
@@ -257,9 +257,9 @@ def standardize_legs(
257
257
  .cast(pl.List(pl.UInt8))
258
258
  .list.set_difference(pl.lit([99])),
259
259
  parking_location=pl.col("TSTAT_VP")
260
- .str.extract("(\w+),?")
260
+ .str.extract(r"(\w+),?")
261
261
  .replace_strict(PARKING_LOCATION_MAP),
262
- parking_type=pl.col("TSTAT_VP").str.extract("(\w+),?").replace_strict(PARKING_TYPE_MAP),
262
+ parking_type=pl.col("TSTAT_VP").str.extract(r"(\w+),?").replace_strict(PARKING_TYPE_MAP),
263
263
  )
264
264
  lf = lf.with_columns(
265
265
  # In some cases, the parking location is a paid location but the person reported a