Skip to content

Instantly share code, notes, and snippets.

View shinichi-takayanagi's full-sized avatar

Shinichi Takaŷanagi shinichi-takayanagi

View GitHub Profile
@shinichi-takayanagi
shinichi-takayanagi / wsl-fix-resolvconf.sh
Created May 3, 2022 23:36 — forked from nfekete/wsl-fix-resolvconf.sh
Fix resolv.conf in Windows Subsystem for Linux, when WSL doesn't correctly generate it.
#!/bin/bash
TMP=`mktemp`
trap ctrlC INT
removeTempFiles() {
rm -f $TMP
}
ctrlC() {
@shinichi-takayanagi
shinichi-takayanagi / snippet.py
Created November 13, 2021 14:36
Pipeline, ColumnTransformer, Pandas
# See https://machinelearningmastery.com/columntransformer-for-numerical-and-categorical-data/
from sklearn.linear_model import LinearRegression
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn import set_config
import seaborn as sns
set_config(display='diagram')
@shinichi-takayanagi
shinichi-takayanagi / snippet.py
Created November 13, 2021 12:27
Grid Search
# https://scikit-learn.org/stable/auto_examples/model_selection/plot_multi_metric_evaluation.html#sphx-glr-auto-examples-model-selection-plot-multi-metric-evaluation-py
# https://machinelearningmastery.com/nested-cross-validation-for-machine-learning-with-python/
from numpy import mean
from numpy import std
from sklearn.datasets import make_classification
from sklearn.metrics import make_scorer, accuracy_score
from sklearn.model_selection import cross_val_score, KFold, RandomizedSearchCV, GridSearchCV, train_test_split
from sklearn.ensemble import RandomForestClassifier
@shinichi-takayanagi
shinichi-takayanagi / snippet.py
Created November 13, 2021 10:30
Classifier Comparison: GradientBoostingClassifier vs XGBClassifier vs LGBMClassifier vs CatBoostClassifier
from numpy import mean
from numpy import std
from sklearn.datasets import make_classification
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
# Models
from sklearn.ensemble import GradientBoostingClassifier
from xgboost import XGBClassifier
from lightgbm import LGBMClassifier
from catboost import CatBoostClassifier
@shinichi-takayanagi
shinichi-takayanagi / snippet.py
Last active November 12, 2021 22:27
Use a Calibrated Model with scikit-learn
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split, StratifiedKFold
from sklearn.datasets import make_classification
# See: https://scikit-learn.org/stable/modules/generated/sklearn.calibration.CalibratedClassifierCV.html
from sklearn.calibration import CalibratedClassifierCV, calibration_curve
# Dummy data (numpy.array)
X, y = make_classification(n_samples=1000, n_classes=2, weights=[1,1], random_state=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=2)
@shinichi-takayanagi
shinichi-takayanagi / snippet.py
Created October 26, 2021 22:27
Snippet for CSV read/write
import csv
# write
with open('names.csv', 'w', newline='') as file:
fieldnames = ['first_name', 'last_name']
writer = csv.DictWriter(file, fieldnames=fieldnames)
writer.writeheader()
writer.writerow({'first_name': 'Baked', 'last_name': 'Beans'})
writer.writerow({'first_name': 'Lovely', 'last_name': 'Spam'})
writer.writerow({'first_name': 'Wonderful', 'last_name': 'Spam'})
# read
@shinichi-takayanagi
shinichi-takayanagi / snippet.py
Created October 26, 2021 22:24
Snippet for multi-class classification problem using scikit-learn
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import cross_val_score, StratifiedKFold
from sklearn.datasets import make_classification, load_iris
from sklearn.metrics import roc_auc_score, make_scorer
from sklearn import set_config
set_config(display='diagram')
pipeline = make_pipeline(LogisticRegression(random_state=0))
pipeline
@shinichi-takayanagi
shinichi-takayanagi / bitbucket-pipelines.yml
Created April 3, 2020 01:23
Docker image build and push to AWS ECR using bitbucket pipelines depending on branch/tag
definitions:
steps:
- step: &build-and-push
script:
- IMAGE_TAG=$(cat TAG.txt)
- echo ${IMAGE_TAG}
- IMAGE_NAME = <your-image-name>
- docker build -t $IMAGE_NAME .
- pipe: atlassian/aws-ecr-push-image:1.1.1
variables:
@shinichi-takayanagi
shinichi-takayanagi / tokyo-bay-area-map.R
Created May 6, 2017 23:15
Tokyo Bay Area Map Generator
library(rvest)
library(stringr)
library(leaflet)
library(RCurl)
library(rjson)
library(RgoogleMaps)
#住所を文字列で入力すると位置情報をjson形式で返却する関数
GetLocationInformation <-function(address)
{