process_mining 0.6.1

Process Mining library for working with (object-centric) event data
Documentation 
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

[package]
name = "process_mining"
version = "0.6.1"
edition = "2021"
license = "MIT OR Apache-2.0"
description = "Process Mining library for working with (object-centric) event data"
homepage = "https://rust4pm.aarkue.eu"
repository = "https://github.com/aarkue/rust4pm"
documentation = "https://docs.rs/process_mining/"
readme = "README.md"
keywords = ["process-mining"]
rust-version = "1.88"

# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

[dependencies]
macros_process_mining = { version = "0.6.1", path = "../macros_process_mining" }
chrono = { version = "0.4.40", features = ["serde"] }
duckdb = { version = "1.2.1", optional = true, features = ["chrono"] }
flate2 = "1.1.1"
graphviz-rust = { version = "0.9.3", optional = true }
itertools = { version = "0.14.0" }
nalgebra = { version = "0.33.2", optional = true }
ordered-float = "5.0.0"
petgraph = "0.8.1"
polars = { version = "0.51.0", features = ["dtype-slim", "timezones", "partition_by"], optional = true }
quick-xml = { version = "0.37.4" }
rand = { version = "0.9.1", optional = true }
rayon = "1.7.0"
regex = { version = "1.11", optional = true }
rusqlite = { version = "0.38.0", features = ["bundled","chrono", "serialize", "column_decltype"], optional = true }
serde_json = "1.0.105"
serde = {version = "1.0.188", features = ["derive"]}
serde_with = { version = "3.16.0", features = ["std", "macros", "schemars_1"]}
tempfile = "3"
uuid = {version = "1.16.0", features = ["v4", "serde"]}
schemars = { version = "1.1.0", features = ["chrono04", "uuid1"]}
inventory = { version = "0.3", optional = true }
# Only for the `bytes` form of a registry-reference argument, i.e. how a host with no filesystem
# hands a log over.
base64 = { version = "0.22", optional = true }
csv = "1.4.0"
# Backends are selected by this crate's own `extraction-dbcon*` features, since not all of them are
# portable. `dbcon`'s `default` is `[]`, and a `dbcon` with no backend recognises no connection
# string, so at least one must be selected.
dbcon = {version = "0.4.1", optional = true }
hashbrown = "0.17.1"
rustc-hash = "2.1.2"
zip = { version = "6", default-features = false, features = ["deflate"], optional = true }
# `default-features = false` drops the unused `arrow` integration; the bundled format's column
# types are written through the low-level row-group writer. `zstd` is needed because `parquet`
# defaults to no block compression, which makes an exported container several times larger than the
# same log as CSV. `snap` is for reading: Snappy is what most other parquet writers emit.
parquet = { version = "58", default-features = false, features = [
    "zstd",
    "snap",
], optional = true }
# Only to hand `parquet` an in-memory `ChunkReader`; `parquet` already depends on it.
bytes = { version = "1", optional = true }

[dev-dependencies]
criterion = { version = "0.5.1", features = ["html_reports"] }
dhat = "0.3.3"

[features]
# Enables exporting Petri nets as PNG/SVG/... images using graphviz.
# Note: graphviz needs to be locally installed to the PATH for the image export functions to work.
graphviz-export = ["dep:graphviz-rust"]

# Enables OCEL 2.0 SQLite/DuckDB import and export functionality
# Note: this might not work on certain architectures or machines if SQLite is not available/cannot be build
ocel-sqlite = ["dep:rusqlite"]
ocel-duckdb = ["dep:duckdb"]
ocel-duckdb-bundled = ["ocel-duckdb", "duckdb/bundled"]

# Enables the relational-to-OCEL extraction blueprint model, validation, SQL compiler, extractor
# and sinks. Carries no connector of its own: `ocel-sqlite` brings `SqliteRowProvider`, and
# `extraction-dbcon` brings the `PostgreSQL`/CSV/Parquet one.
extraction-blueprint = ["dep:regex"]

# Adds `DbconRowProvider`, a `RowProvider` over the file-backed sources `dbcon` reads (SQLite, CSV
# and Parquet), and the extraction bindings that open one.
#
# Excludes PostgreSQL, which is `extraction-dbcon-postgres` below. These three build for
# `wasm32-unknown-unknown` (`dbcon` substitutes `sqlite-wasm-rs` there) and can be read from bytes
# with no filesystem, as a browser needs. Bundling PostgreSQL here would pull `sqlx` and its
# runtime into every build that only wants to read a dropped CSV.
extraction-dbcon = [
    "dep:dbcon",
    "extraction-blueprint",
    "dbcon/sqlite",
    "dbcon/csv",
    "dbcon/parquet",
    # Pure Rust and byte-readable, so it belongs with the wasm-capable three.
    "dbcon/xlsx",
]

# Adds PostgreSQL to `extraction-dbcon`. Separate because `sqlx` does not build for
# `wasm32-unknown-unknown`, and because a server connection is meaningless from a browser page.
extraction-dbcon-postgres = ["extraction-dbcon", "dbcon/postgres"]

# Adds DuckDB to `extraction-dbcon`. Separate for the same reason as PostgreSQL: the `duckdb` crate
# builds native code and does not build for `wasm32`.
extraction-dbcon-duckdb = ["extraction-dbcon", "dbcon/duckdb"]
extraction-dbcon-duckdb-bundled = ["extraction-dbcon-duckdb", "dbcon/duckdb-bundled"]

# Enables reading and writing the OCEL 2.0 bundled CSV/Parquet format: a `.ocel.zip` archive or
# a directory with the same layout, with CSV storage.
ocel-bundle = ["dep:zip"]

# Adds Parquet storage to `ocel-bundle`. Separate because `parquet` is a large dependency and
# a CSV container needs none of it.
ocel-bundle-parquet = ["ocel-bundle", "dep:parquet", "dep:bytes"]

# Enables polars DataFrame conversion from/to event data structs
dataframes = ["dep:polars"]

# Enables event log splitting (+rand dependency)
log-splitting = ["dep:rand"]

# Enables algebraic functionality
token-based-replay = ["dep:nalgebra"]

# Enable bindings
bindings = [
   "dep:inventory",
   "dep:base64"
]

all = ["graphviz-export","ocel-sqlite","ocel-duckdb-bundled","extraction-blueprint","extraction-dbcon","extraction-dbcon-postgres","extraction-dbcon-duckdb-bundled","ocel-bundle","ocel-bundle-parquet","dataframes", "log-splitting", "token-based-replay", "bindings" ]

[package.metadata.docs.rs]
# The same set as `all`, listed explicitly so a feature docs.rs cannot build can be dropped
# individually.
features = [
    "graphviz-export",
    "ocel-sqlite",
    "ocel-duckdb-bundled",
    "extraction-blueprint",
    "extraction-dbcon",
    "extraction-dbcon-postgres",
    "extraction-dbcon-duckdb-bundled",
    "ocel-bundle",
    "ocel-bundle-parquet",
    "dataframes",
    "log-splitting",
    "token-based-replay",
    "bindings",
]

[[example]]
name = "ocel_duckdb_export"
required-features = ["ocel-duckdb"]

[[bench]]
name = "load_dataframe"
harness = false
required-features = ["dataframes"]

[[bench]]
name = "load_dataframe_mem"
harness = false
required-features = ["dataframes"]

[[bench]]
name = "load_events"
harness = false

[[bench]]
name = "load_events_mem"
harness = false

[[bench]]
name = "alignments"
harness = false

[[bench]]
name = "ocel_import"
harness = false
required-features = ["ocel-duckdb"]

[[example]]
name = "ocel_stream_to_duckdb"
required-features = ["ocel-duckdb"]

[[example]]
name = "ocel_dataset_crosscheck"
required-features = ["ocel-bundle-parquet"]