koodiklinikka/palkkakysely
1
0
Fork 0
mirror of https://github.com/koodiklinikka/palkkakysely.git synced 2026-02-21 08:55:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #18 from koodiklinikka/2024

Browse Source 
2024 Edition
This commit is contained in:
Aarni Koskela
2024-10-28 11:54:13 +02:00
committed by GitHub
parent 001610bbc3 81fc15a541
commit 8784f379eb
14 changed files with 175 additions and 148 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
.github/workflows/build.yml vendored
View File

@@ -14,26 +14,27 @@ jobs:
lint: lint:
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v4
- uses: actions/setup-python@v4 - uses: actions/setup-python@v5
with: with:
python-version: "3.11" python-version: "3.12"
cache: pip cache: pip
- uses: pre-commit/action@v3.0.0 - uses: pre-commit/action@v3.0.1
build: build:
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v4
- name: Set up Python 3.11 - uses: actions/setup-python@v5
uses: actions/setup-python@v4
with: with:
python-version: "3.11" python-version: "3.12"
cache: pip - uses: astral-sh/setup-uv@v3
- name: Install dependencies with:
run: python -m pip install -r requirements.txt version: "0.4.x"
- name: Build enable-cache: true
run: make -j3 cache-dependency-glob: "**/requirements*.txt"
- uses: actions/setup-node@v3 - run: uv pip install --system -r requirements.txt
- run: make -j3
- uses: actions/setup-node@v4
with: with:
node-version: "20" node-version: "20"
cache: yarn cache: yarn

9
.pre-commit-config.yaml
View File

@@ -3,16 +3,13 @@ ci:
autofix_prs: false autofix_prs: false
repos: repos:
- repo: https://github.com/astral-sh/ruff-pre-commit - repo: https://github.com/astral-sh/ruff-pre-commit
rev: v0.0.291 rev: v0.7.1
hooks: hooks:
- id: ruff - id: ruff
args: args:
- --fix - --fix
- repo: https://github.com/psf/black - id: ruff-format
rev: 23.9.1
hooks:
- id: black
- repo: https://github.com/pre-commit/mirrors-prettier - repo: https://github.com/pre-commit/mirrors-prettier
rev: v3.0.3 rev: v3.1.0
hooks: hooks:
- id: prettier - id: prettier

6
Makefile
View File

@@ -1,8 +1,8 @@
YEAR := 2023 YEAR := 2024
DATA_DIR := data/${YEAR} DATA_DIR := data/${YEAR}
OUT_DIR := out/${YEAR} OUT_DIR := out/${YEAR}
DOCUMENT_ID_FI := 1sycmd6DGqHj9-0k6D8HclzlRghxqoVaBZNSZye1Jdbg DOCUMENT_ID_FI := 1dvyVEJkn3_osBeKGIlhKmid671jjH7zYgcyH1BjiGF8
DOCUMENT_ID_EN := 1pmrQWsja3wRVF02PyEGO2F_CgttobTbxGUGjQ5K4H4Y DOCUMENT_ID_EN := 1o1uakk1pkoUCtx2OGJhLclxt_uraYA-uK3DH8yCYHN4
XLSX_URL_FI := https://docs.google.com/spreadsheets/d/$(DOCUMENT_ID_FI)/export?format=xlsx XLSX_URL_FI := https://docs.google.com/spreadsheets/d/$(DOCUMENT_ID_FI)/export?format=xlsx
TSV_URL_FI := https://docs.google.com/spreadsheets/d/$(DOCUMENT_ID_FI)/export?format=tsv TSV_URL_FI := https://docs.google.com/spreadsheets/d/$(DOCUMENT_ID_FI)/export?format=tsv
XLSX_URL_EN := https://docs.google.com/spreadsheets/d/$(DOCUMENT_ID_EN)/export?format=xlsx XLSX_URL_EN := https://docs.google.com/spreadsheets/d/$(DOCUMENT_ID_EN)/export?format=xlsx

1
out/index.html
View File

@@ -14,6 +14,7 @@
<li><a href="2021/">2021</a></li> <li><a href="2021/">2021</a></li>
<li><a href="2022/">2022</a></li> <li><a href="2022/">2022</a></li>
<li><a href="2023/">2023</a></li> <li><a href="2023/">2023</a></li>
<li><a href="2024/">2024</a></li>
</ul> </ul>
</body> </body>
</html> </html>

3
pulkka/chart_utils.py
View File

@@ -1,4 +1,5 @@
from bokeh import models as bm, plotting as bp from bokeh import models as bm
from bokeh import plotting as bp
from bokeh.transform import factor_cmap from bokeh.transform import factor_cmap
from pandas import DataFrame from pandas import DataFrame

65
pulkka/column_maps.py
View File

@@ -19,7 +19,7 @@ PALVELUT_COL = "Palvelut"
ROOLI_COL = "Rooli" ROOLI_COL = "Rooli"
ROOLI_NORM_COL = "Rooli (normalisoitu)" ROOLI_NORM_COL = "Rooli (normalisoitu)"
SIIRTYNYT_COL = ( SIIRTYNYT_COL = (
"Oletko siirtynyt palkansaajasta laskuttajaksi tai päinvastoin 1.10.2022 jälkeen?" "Oletko siirtynyt palkansaajasta laskuttajaksi tai päinvastoin 1.10.2023 jälkeen?"
) )
SUKUPUOLI_COL = "Sukupuoli" SUKUPUOLI_COL = "Sukupuoli"
TUNTILASKUTUS_ALV0_COL = "Tuntilaskutus (ALV 0%, euroina)" TUNTILASKUTUS_ALV0_COL = "Tuntilaskutus (ALV 0%, euroina)"
@@ -30,10 +30,10 @@ VUOSILASKUTUS_ALV0_COL = "Vuosilaskutus (ALV 0%, euroina)"
VUOSITULOT_COL = "Vuositulot" VUOSITULOT_COL = "Vuositulot"
ID_COL = "Vastaustunniste" ID_COL = "Vastaustunniste"
COLUMN_MAP_2023 = { COLUMN_MAP_2024 = {
"Timestamp": "Timestamp", "Timestamp": "Timestamp",
"Oletko palkansaaja vai laskuttaja?": PALKANSAAJA_VAI_LASKUTTAJA_COL, "Oletko palkansaaja vai laskuttaja?": PALKANSAAJA_VAI_LASKUTTAJA_COL,
"Oletko siirtynyt palkansaajasta laskuttajaksi tai päinvastoin 1.10.2022 jälkeen?": SIIRTYNYT_COL, "Oletko siirtynyt palkansaajasta laskuttajaksi tai päinvastoin 1.10.2023 jälkeen?": SIIRTYNYT_COL,
"Ikä": "Ikä", "Ikä": "Ikä",
"Sukupuoli": "Sukupuoli", "Sukupuoli": "Sukupuoli",
"Työkokemus alalta (vuosina)": TYOKOKEMUS_COL, "Työkokemus alalta (vuosina)": TYOKOKEMUS_COL,
@@ -59,10 +59,10 @@ COLUMN_MAP_2023 = {
"Palautetta kyselystä ja ideoita ensi vuoden kyselyyn": PALAUTE_COL, "Palautetta kyselystä ja ideoita ensi vuoden kyselyyn": PALAUTE_COL,
} }
COLUMN_MAP_2023_EN_TO_FI = { COLUMN_MAP_2024_EN_TO_FI = {
"Timestamp": "Timestamp", "Timestamp": "Timestamp",
"Employee or entrepreneur": "Oletko palkansaaja vai laskuttaja?", "Employee or entrepreneur": "Oletko palkansaaja vai laskuttaja?",
"Have you switched from employment to entrepreneurship or vice versa after 1.10.2022?": "Oletko siirtynyt palkansaajasta laskuttajaksi tai päinvastoin 1.10.2022 jälkeen?", "Have you switched from employment to entrepreneurship or vice versa after 1.10.2023?": "Oletko siirtynyt palkansaajasta laskuttajaksi tai päinvastoin 1.10.2023 jälkeen?",
"Age": "Ikä", "Age": "Ikä",
"Gender": "Sukupuoli", "Gender": "Sukupuoli",
"Relevant work experience from the industry (in years)": "Työkokemus alalta (vuosina)", "Relevant work experience from the industry (in years)": "Työkokemus alalta (vuosina)",
@@ -89,9 +89,9 @@ COLUMN_MAP_2023_EN_TO_FI = {
} }
# ensure all columns have translations # ensure all columns have translations
assert set(COLUMN_MAP_2023.keys()) == set(COLUMN_MAP_2023_EN_TO_FI.values()) assert set(COLUMN_MAP_2024.keys()) == set(COLUMN_MAP_2024_EN_TO_FI.values())
VALUE_MAP_2023_EN_TO_FI = { VALUE_MAP_2024_EN_TO_FI = {
PALKANSAAJA_VAI_LASKUTTAJA_COL: { PALKANSAAJA_VAI_LASKUTTAJA_COL: {
"Employee": "Palkansaaja", "Employee": "Palkansaaja",
"Entrepreneur": "Laskuttaja", "Entrepreneur": "Laskuttaja",
@@ -112,8 +112,16 @@ VALUE_MAP_2023_EN_TO_FI = {
"Finland": "Suomesta", "Finland": "Suomesta",
}, },
KAUPUNKI_COL: { KAUPUNKI_COL: {
"PK-Seutu (Helsinki, Espoo, Vantaa)": "PK-seutu", "Asun Porissa, toimisto Helsingissä, sijainnilla ei vaikutusta palkkaan": "Pori",
"Capital region (Helsinki, Espoo, Vantaa)": "PK-seutu", "Capital region (Helsinki, Espoo, Vantaa)": "PK-seutu",
"Firmalla ei ole toimistoa": "Etätyöfirma",
"Hajautettu": "Etätyöfirma",
"New York City": "New York",
"New York, NY, USA": "New York",
"PK-Seutu (Helsinki, Espoo, Vantaa)": "PK-seutu",
"Tampere (etänä Berliiniin)": "Tampere",
"Turku/remote (HQ Austin, TX)": "Turku",
"Ulkomailla": "Ulkomaat",
}, },
MILLAISESSA_COL: { MILLAISESSA_COL: {
"Product company with softaware as their core business": "Tuotetalossa, jonka core-bisnes on softa", "Product company with softaware as their core business": "Tuotetalossa, jonka core-bisnes on softa",
@@ -166,23 +174,44 @@ ROLE_MAP = {
"Full-stack cloud developer": FULL_STACK_ROLE, "Full-stack cloud developer": FULL_STACK_ROLE,
"Fullstack developer, web apps": FULL_STACK_ROLE, "Fullstack developer, web apps": FULL_STACK_ROLE,
} }
NO_GENDER_VALUES = { NO_GENDER_VALUES = {
"-", "-",
"ei liity asiaan", "on",
"epärelevantti",
"jänis",
"kyllä, kiitos",
"leppäkerttu",
"tihkutympönen",
"yes", "yes",
} }
OTHER_GENDER_VALUES = { OTHER_GENDER_VALUES = {
"muu", "muu",
"muu/ei", "muunsukupuolinen",
"non-binary, afab",
} }
FEMALE_GENDER_VALUES = (
"f",
"n",
"women",
)
MALE_GENDER_VALUES = (
"he / him / male",
"ihminen. kikkelillä.",
"m i ä s",
"m",
"mail", # probably a typo
"male presenting",
"male",
"man",
"meis",
"mie", # probably mies?
"miekkonen",
"mies",
"miesoletettu",
"miäs",
"ukko",
"äiä",
)
IDS_TO_DROP = { IDS_TO_DROP = {
"6cab61607da9c2b6", # hupsu taisteluhelikopteri "0bf579f8b0a771b9", # 2 euron palkka, rooli "2"
"aefdb9e69b1621d5", # See "SUBMITTED TWICE, SORRY!!" in English data "9a3b73d810f6e983", # apache hyökkäyshelikopteri
} }

84
pulkka/data_ingest.py
View File

@@ -8,35 +8,37 @@ import numpy as np
import pandas import pandas
import pandas as pd import pandas as pd
from pulkka.config import DATA_DIR, YEAR
from pulkka.column_maps import ( from pulkka.column_maps import (
COLUMN_MAP_2023_EN_TO_FI,
KIKY_COL,
KKPALKKA_COL,
PALVELUT_COL,
TYOAIKA_COL,
VUOSITULOT_COL,
TYOPAIKKA_COL,
ROOLI_COL,
KIKY_OTHER_COL,
BOOLEAN_TEXT_TO_BOOLEAN_MAP, BOOLEAN_TEXT_TO_BOOLEAN_MAP,
COLUMN_MAP_2024,
COLUMN_MAP_2024_EN_TO_FI,
COMPANY_MAP, COMPANY_MAP,
SUKUPUOLI_COL, FEMALE_GENDER_VALUES,
ROLE_MAP,
COLUMN_MAP_2023,
VALUE_MAP_2023_EN_TO_FI,
LAHITYO_COL,
IKA_COL,
LANG_COL,
KK_TULOT_COL,
KK_TULOT_NORM_COL,
NO_GENDER_VALUES,
OTHER_GENDER_VALUES,
TYOKOKEMUS_COL,
ROOLI_NORM_COL,
ID_COL, ID_COL,
IDS_TO_DROP, IDS_TO_DROP,
IKA_COL,
KIKY_COL,
KIKY_OTHER_COL,
KK_TULOT_COL,
KK_TULOT_NORM_COL,
KKPALKKA_COL,
LAHITYO_COL,
LANG_COL,
MALE_GENDER_VALUES,
NO_GENDER_VALUES,
OTHER_GENDER_VALUES,
PALVELUT_COL,
ROLE_MAP,
ROOLI_COL,
ROOLI_NORM_COL,
SUKUPUOLI_COL,
TYOAIKA_COL,
TYOKOKEMUS_COL,
TYOPAIKKA_COL,
VALUE_MAP_2024_EN_TO_FI,
VUOSITULOT_COL,
) )
from pulkka.config import DATA_DIR, YEAR
def map_sukupuoli(r: pd.Series) -> str | None: def map_sukupuoli(r: pd.Series) -> str | None:
@@ -49,19 +51,11 @@ def map_sukupuoli(r: pd.Series) -> str | None:
"nainen" in value "nainen" in value
or "female" in value or "female" in value
or "woman" in value or "woman" in value
or value == "f" or value in FEMALE_GENDER_VALUES
or value == "women"
): ):
return "nainen" return "nainen"
if ( if value.strip() in MALE_GENDER_VALUES:
"mies" in value
or "uros" in value
or "miäs" in value
or "äiä" in value
or "male" in value
or value in ("m", "man", "m i ä s", "ukko")
):
return "mies" return "mies"
if value in NO_GENDER_VALUES: if value in NO_GENDER_VALUES:
@@ -70,7 +64,7 @@ def map_sukupuoli(r: pd.Series) -> str | None:
if value in OTHER_GENDER_VALUES: if value in OTHER_GENDER_VALUES:
return "muu" return "muu"
raise NotImplementedError(f"Unknown sukupuoli: {value} (row ID {r[ID_COL]})") raise NotImplementedError(f"Unknown sukupuoli: {value!r} (row ID {r[ID_COL]})")
def map_vuositulot(r): def map_vuositulot(r):
@@ -110,7 +104,7 @@ def read_initial_dfs() -> pd.DataFrame:
skiprows=[1], # Google Sheets exports one empty row skiprows=[1], # Google Sheets exports one empty row
) )
df_en[LANG_COL] = "en" df_en[LANG_COL] = "en"
df_en = df_en.rename(columns=COLUMN_MAP_2023_EN_TO_FI) df_en = df_en.rename(columns=COLUMN_MAP_2024_EN_TO_FI)
df = pd.concat([df_fi, df_en], ignore_index=True) df = pd.concat([df_fi, df_en], ignore_index=True)
df = df[df["Timestamp"].notna()] # Remove rows with no timestamp df = df[df["Timestamp"].notna()] # Remove rows with no timestamp
df[LANG_COL] = df[LANG_COL].astype("category") df[LANG_COL] = df[LANG_COL].astype("category")
@@ -130,23 +124,24 @@ def map_case_insensitive(series: pd.Series, mapping: dict[str, str]) -> pd.Serie
def map_value(v): def map_value(v):
if v is np.nan: if v is np.nan:
return "" return ""
assert isinstance(v, str) if not isinstance(v, str):
raise TypeError(f"Unexpected value {v!r} of type {type(v)}")
return lower_mapping.get(v.lower().strip(), v) return lower_mapping.get(v.lower().strip(), v)
return series.apply(map_value).fillna(series) return series.apply(map_value).fillna(series)
def read_data() -> pd.DataFrame: def read_data() -> pd.DataFrame:
if YEAR != "2023": if YEAR != "2024":
raise ValueError( raise ValueError(
"This code only works for 2023. " "This code only works for 2024. "
"Please use an older revision for older data.", "Please use an older revision for older data.",
) )
df = read_initial_dfs() df = read_initial_dfs()
df = df.rename(columns=COLUMN_MAP_2023) df = df.rename(columns=COLUMN_MAP_2024)
for col, val_map in VALUE_MAP_2023_EN_TO_FI.items(): for col, val_map in VALUE_MAP_2024_EN_TO_FI.items():
df[col] = df[col].map(val_map).fillna(df[col]).astype("category") df[col] = df[col].map(val_map).fillna(df[col]).astype("category")
# Drop known bogus data # Drop known bogus data
@@ -192,14 +187,7 @@ def read_data() -> pd.DataFrame:
df = apply_fixups( df = apply_fixups(
df, df,
[ [
( # ({ID_COL: "..."}, {VUOSITULOT_COL: 62000}),
{ID_COL: "a01216a11026d749", VUOSITULOT_COL: 620000},
{VUOSITULOT_COL: 62000},
),
(
{ID_COL: "79a200f529f6919b", VUOSITULOT_COL: 1500},
{VUOSITULOT_COL: 150_000},
),
], ],
) )
# Fill in Vuositulot as 12.5 * Kk-tulot if empty # Fill in Vuositulot as 12.5 * Kk-tulot if empty

2
pulkka/data_utils.py
View File

@@ -33,7 +33,7 @@ def get_categorical_stats(
if na_as_category: if na_as_category:
rename_na(df, category_col, na_as_category) rename_na(df, category_col, na_as_category)
# ... then carry on. # ... then carry on.
group = df[[category_col, value_col]].groupby(category_col) group = df[[category_col, value_col]].groupby(category_col, observed=False)
return group[value_col].agg( return group[value_col].agg(
["mean", "min", "max", "median", "count", q25, q50, q75, q90], ["mean", "min", "max", "median", "count", q25, q50, q75, q90],
) )

12
pulkka/generate_charts.py
View File

@@ -1,20 +1,20 @@
import bokeh.plotting as bp
import bokeh.models as bm
import bokeh.layouts as bl import bokeh.layouts as bl
import bokeh.models as bm
import bokeh.plotting as bp
from pandas import DataFrame from pandas import DataFrame
from pulkka.chart_utils import ( from pulkka.chart_utils import (
gender_colormap, gender_colormap,
get_categorical_stats_plot,
get_df_hover_tool, get_df_hover_tool,
set_yaxis_cash, set_yaxis_cash,
get_categorical_stats_plot,
) )
from pulkka.column_maps import ( from pulkka.column_maps import (
IKA_COL,
KAUPUNKI_COL,
SUKUPUOLI_COL,
TYOKOKEMUS_COL, TYOKOKEMUS_COL,
VUOSITULOT_COL, VUOSITULOT_COL,
KAUPUNKI_COL,
IKA_COL,
SUKUPUOLI_COL,
) )
from pulkka.config import OUT_DIR from pulkka.config import OUT_DIR
from pulkka.data_ingest import read_data from pulkka.data_ingest import read_data

4
pulkka/generate_profiling.py
View File

@@ -1,9 +1,9 @@
import pandas as pd import pandas as pd
from ydata_profiling import ProfileReport
from pulkka.column_maps import KKPALKKA_COL, VUOSITULOT_COL from pulkka.column_maps import KKPALKKA_COL, VUOSITULOT_COL
from pulkka.config import OUT_DIR from pulkka.config import OUT_DIR
from pulkka.data_ingest import read_data, force_age_numeric from pulkka.data_ingest import force_age_numeric, read_data
from ydata_profiling import ProfileReport
def main(): def main():

2
pulkka/massage_outputs.py
View File

@@ -79,7 +79,7 @@ def main():
) )
env.globals.update( env.globals.update(
{ {
"date": datetime.datetime.utcnow(), "date": datetime.datetime.now(datetime.UTC),
"cm": column_maps, "cm": column_maps,
"pd": pandas, "pd": pandas,
"np": numpy, "np": numpy,

1
requirements.in
View File

@@ -3,4 +3,5 @@ jinja2
matplotlib<3.8.0 # ydata-profiling compat matplotlib<3.8.0 # ydata-profiling compat
openpyxl openpyxl
pandas pandas
setuptools # implicitly required by ydata-profiling
ydata-profiling ydata-profiling

103
requirements.txt
View File

@@ -1,65 +1,68 @@
# # This file was autogenerated by uv via the following command:
# This file is autogenerated by pip-compile with Python 3.11 # uv pip compile requirements.in -o requirements.txt
# by the following command: annotated-types==0.7.0
# # via pydantic
# pip-compile requirements.in attrs==24.2.0
#
attrs==23.1.0
# via visions # via visions
bokeh==2.4.3 bokeh==2.4.3
# via -r requirements.in # via -r requirements.in
certifi==2023.7.22 certifi==2024.8.30
# via requests # via requests
charset-normalizer==3.2.0 charset-normalizer==3.4.0
# via requests # via requests
contourpy==1.1.1 contourpy==1.3.0
# via matplotlib # via matplotlib
cycler==0.11.0 cycler==0.12.1
# via matplotlib # via matplotlib
dacite==1.8.1 dacite==1.8.1
# via ydata-profiling # via ydata-profiling
et-xmlfile==1.1.0 et-xmlfile==1.1.0
# via openpyxl # via openpyxl
fonttools==4.42.1 fonttools==4.54.1
# via matplotlib # via matplotlib
htmlmin==0.1.12 htmlmin==0.1.12
# via ydata-profiling # via ydata-profiling
idna==3.4 idna==3.10
# via requests # via requests
imagehash==4.3.1 imagehash==4.3.1
# via # via
# visions # visions
# ydata-profiling # ydata-profiling
jinja2==3.1.2 jinja2==3.1.4
# via # via
# -r requirements.in # -r requirements.in
# bokeh # bokeh
# ydata-profiling # ydata-profiling
joblib==1.3.2 joblib==1.4.2
# via phik # via phik
kiwisolver==1.4.5 kiwisolver==1.4.7
# via matplotlib # via matplotlib
markupsafe==2.1.3 llvmlite==0.43.0
# via numba
markupsafe==3.0.1
# via jinja2 # via jinja2
matplotlib==3.7.3 matplotlib==3.7.5
# via # via
# -r requirements.in # -r requirements.in
# phik # phik
# seaborn # seaborn
# wordcloud # wordcloud
# ydata-profiling # ydata-profiling
multimethod==1.10 multimethod==1.12
# via # via
# visions # visions
# ydata-profiling # ydata-profiling
networkx==3.1 networkx==3.4.1
# via visions # via visions
numpy==1.23.5 numba==0.60.0
# via ydata-profiling
numpy==1.26.4
# via # via
# bokeh # bokeh
# contourpy # contourpy
# imagehash # imagehash
# matplotlib # matplotlib
# numba
# pandas # pandas
# patsy # patsy
# phik # phik
@@ -70,14 +73,14 @@ numpy==1.23.5
# visions # visions
# wordcloud # wordcloud
# ydata-profiling # ydata-profiling
openpyxl==3.1.2 openpyxl==3.1.5
# via -r requirements.in # via -r requirements.in
packaging==23.1 packaging==24.1
# via # via
# bokeh # bokeh
# matplotlib # matplotlib
# statsmodels # statsmodels
pandas==2.0.3 pandas==2.2.3
# via # via
# -r requirements.in # -r requirements.in
# phik # phik
@@ -85,68 +88,72 @@ pandas==2.0.3
# statsmodels # statsmodels
# visions # visions
# ydata-profiling # ydata-profiling
patsy==0.5.3 patsy==0.5.6
# via statsmodels # via statsmodels
phik==0.12.3 phik==0.12.4
# via ydata-profiling # via ydata-profiling
pillow==10.0.1 pillow==11.0.0
# via # via
# bokeh # bokeh
# imagehash # imagehash
# matplotlib # matplotlib
# visions # visions
# wordcloud # wordcloud
pydantic==1.10.12 pydantic==2.9.2
# via ydata-profiling # via ydata-profiling
pyparsing==3.1.1 pydantic-core==2.23.4
# via pydantic
pyparsing==3.2.0
# via matplotlib # via matplotlib
python-dateutil==2.8.2 python-dateutil==2.9.0.post0
# via # via
# matplotlib # matplotlib
# pandas # pandas
pytz==2023.3.post1 pytz==2024.2
# via pandas # via pandas
pywavelets==1.4.1 pywavelets==1.7.0
# via imagehash # via imagehash
pyyaml==6.0.1 pyyaml==6.0.2
# via # via
# bokeh # bokeh
# ydata-profiling # ydata-profiling
requests==2.31.0 requests==2.32.3
# via ydata-profiling # via ydata-profiling
scipy==1.11.2 scipy==1.13.1
# via # via
# imagehash # imagehash
# phik # phik
# statsmodels # statsmodels
# ydata-profiling # ydata-profiling
seaborn==0.12.2 seaborn==0.13.2
# via ydata-profiling # via ydata-profiling
setuptools==75.2.0
# via -r requirements.in
six==1.16.0 six==1.16.0
# via # via
# patsy # patsy
# python-dateutil # python-dateutil
statsmodels==0.14.0 statsmodels==0.14.4
# via ydata-profiling # via ydata-profiling
tangled-up-in-unicode==0.2.0 tornado==6.4.1
# via visions
tornado==6.3.3
# via bokeh # via bokeh
tqdm==4.66.1 tqdm==4.66.5
# via ydata-profiling # via ydata-profiling
typeguard==2.13.3 typeguard==4.3.0
# via ydata-profiling # via ydata-profiling
typing-extensions==4.8.0 typing-extensions==4.12.2
# via # via
# bokeh # bokeh
# pydantic # pydantic
tzdata==2023.3 # pydantic-core
# typeguard
tzdata==2024.2
# via pandas # via pandas
urllib3==2.0.5 urllib3==2.2.3
# via requests # via requests
visions[type_image_path]==0.7.5 visions==0.7.6
# via ydata-profiling # via ydata-profiling
wordcloud==1.9.2 wordcloud==1.9.3
# via ydata-profiling # via ydata-profiling
ydata-profiling==4.5.1 ydata-profiling==4.11.0
# via -r requirements.in # via -r requirements.in

2
ruff.toml
View File

@@ -1,8 +1,10 @@
[lint]
ignore = [ ignore = [
"E501", "E501",
"PD901", # I know "df" isn't the best name "PD901", # I know "df" isn't the best name
] ]
extend-select = [ extend-select = [
"COM", "COM",
"I",
"PD", "PD",
] ]