This commit is contained in:
ulaniuk 2022-06-05 09:09:13 +02:00
parent b36d200b4b
commit e26eb37462
15 changed files with 582 additions and 4 deletions

3
.dvc/.gitignore vendored Normal file
View File

@ -0,0 +1,3 @@
/config.local
/tmp
/cache

5
.dvc/config Normal file
View File

@ -0,0 +1,5 @@
[core]
remote = ium_ssh_remote
['remote "ium_ssh_remote"']
url = ssh://ium-sftp@tzietkiewicz.vm.wmi.amu.edu.pl
user = ium-sftp

107
.dvc/plots/confusion.json Normal file
View File

@ -0,0 +1,107 @@
{
"$schema": "https://vega.github.io/schema/vega-lite/v4.json",
"data": {
"values": "<DVC_METRIC_DATA>"
},
"title": "<DVC_METRIC_TITLE>",
"facet": {
"field": "rev",
"type": "nominal"
},
"spec": {
"transform": [
{
"aggregate": [
{
"op": "count",
"as": "xy_count"
}
],
"groupby": [
"<DVC_METRIC_Y>",
"<DVC_METRIC_X>"
]
},
{
"impute": "xy_count",
"groupby": [
"rev",
"<DVC_METRIC_Y>"
],
"key": "<DVC_METRIC_X>",
"value": 0
},
{
"impute": "xy_count",
"groupby": [
"rev",
"<DVC_METRIC_X>"
],
"key": "<DVC_METRIC_Y>",
"value": 0
},
{
"joinaggregate": [
{
"op": "max",
"field": "xy_count",
"as": "max_count"
}
],
"groupby": []
},
{
"calculate": "datum.xy_count / datum.max_count",
"as": "percent_of_max"
}
],
"encoding": {
"x": {
"field": "<DVC_METRIC_X>",
"type": "nominal",
"sort": "ascending",
"title": "<DVC_METRIC_X_LABEL>"
},
"y": {
"field": "<DVC_METRIC_Y>",
"type": "nominal",
"sort": "ascending",
"title": "<DVC_METRIC_Y_LABEL>"
}
},
"layer": [
{
"mark": "rect",
"width": 300,
"height": 300,
"encoding": {
"color": {
"field": "xy_count",
"type": "quantitative",
"title": "",
"scale": {
"domainMin": 0,
"nice": true
}
}
}
},
{
"mark": "text",
"encoding": {
"text": {
"field": "xy_count",
"type": "quantitative"
},
"color": {
"condition": {
"test": "datum.percent_of_max > 0.5",
"value": "white"
},
"value": "black"
}
}
}
]
}
}

View File

@ -0,0 +1,112 @@
{
"$schema": "https://vega.github.io/schema/vega-lite/v4.json",
"data": {
"values": "<DVC_METRIC_DATA>"
},
"title": "<DVC_METRIC_TITLE>",
"facet": {
"field": "rev",
"type": "nominal"
},
"spec": {
"transform": [
{
"aggregate": [
{
"op": "count",
"as": "xy_count"
}
],
"groupby": [
"<DVC_METRIC_Y>",
"<DVC_METRIC_X>"
]
},
{
"impute": "xy_count",
"groupby": [
"rev",
"<DVC_METRIC_Y>"
],
"key": "<DVC_METRIC_X>",
"value": 0
},
{
"impute": "xy_count",
"groupby": [
"rev",
"<DVC_METRIC_X>"
],
"key": "<DVC_METRIC_Y>",
"value": 0
},
{
"joinaggregate": [
{
"op": "sum",
"field": "xy_count",
"as": "sum_y"
}
],
"groupby": [
"<DVC_METRIC_Y>"
]
},
{
"calculate": "datum.xy_count / datum.sum_y",
"as": "percent_of_y"
}
],
"encoding": {
"x": {
"field": "<DVC_METRIC_X>",
"type": "nominal",
"sort": "ascending",
"title": "<DVC_METRIC_X_LABEL>"
},
"y": {
"field": "<DVC_METRIC_Y>",
"type": "nominal",
"sort": "ascending",
"title": "<DVC_METRIC_Y_LABEL>"
}
},
"layer": [
{
"mark": "rect",
"width": 300,
"height": 300,
"encoding": {
"color": {
"field": "percent_of_y",
"type": "quantitative",
"title": "",
"scale": {
"domain": [
0,
1
]
}
}
}
},
{
"mark": "text",
"encoding": {
"text": {
"field": "percent_of_y",
"type": "quantitative",
"format": ".2f"
},
"color": {
"condition": {
"test": "datum.percent_of_y > 0.5",
"value": "white"
},
"value": "black"
}
}
}
]
}
}

31
.dvc/plots/default.json Normal file
View File

@ -0,0 +1,31 @@
{
"$schema": "https://vega.github.io/schema/vega-lite/v4.json",
"data": {
"values": "<DVC_METRIC_DATA>"
},
"title": "<DVC_METRIC_TITLE>",
"width": 300,
"height": 300,
"mark": {
"type": "line"
},
"encoding": {
"x": {
"field": "<DVC_METRIC_X>",
"type": "quantitative",
"title": "<DVC_METRIC_X_LABEL>"
},
"y": {
"field": "<DVC_METRIC_Y>",
"type": "quantitative",
"title": "<DVC_METRIC_Y_LABEL>",
"scale": {
"zero": false
}
},
"color": {
"field": "rev",
"type": "nominal"
}
}
}

116
.dvc/plots/linear.json Normal file
View File

@ -0,0 +1,116 @@
{
"$schema": "https://vega.github.io/schema/vega-lite/v4.json",
"data": {
"values": "<DVC_METRIC_DATA>"
},
"title": "<DVC_METRIC_TITLE>",
"width": 300,
"height": 300,
"layer": [
{
"encoding": {
"x": {
"field": "<DVC_METRIC_X>",
"type": "quantitative",
"title": "<DVC_METRIC_X_LABEL>"
},
"y": {
"field": "<DVC_METRIC_Y>",
"type": "quantitative",
"title": "<DVC_METRIC_Y_LABEL>",
"scale": {
"zero": false
}
},
"color": {
"field": "rev",
"type": "nominal"
}
},
"layer": [
{
"mark": "line"
},
{
"selection": {
"label": {
"type": "single",
"nearest": true,
"on": "mouseover",
"encodings": [
"x"
],
"empty": "none",
"clear": "mouseout"
}
},
"mark": "point",
"encoding": {
"opacity": {
"condition": {
"selection": "label",
"value": 1
},
"value": 0
}
}
}
]
},
{
"transform": [
{
"filter": {
"selection": "label"
}
}
],
"layer": [
{
"mark": {
"type": "rule",
"color": "gray"
},
"encoding": {
"x": {
"field": "<DVC_METRIC_X>",
"type": "quantitative"
}
}
},
{
"encoding": {
"text": {
"type": "quantitative",
"field": "<DVC_METRIC_Y>"
},
"x": {
"field": "<DVC_METRIC_X>",
"type": "quantitative"
},
"y": {
"field": "<DVC_METRIC_Y>",
"type": "quantitative"
}
},
"layer": [
{
"mark": {
"type": "text",
"align": "left",
"dx": 5,
"dy": -5
},
"encoding": {
"color": {
"type": "nominal",
"field": "rev"
}
}
}
]
}
]
}
]
}

104
.dvc/plots/scatter.json Normal file
View File

@ -0,0 +1,104 @@
{
"$schema": "https://vega.github.io/schema/vega-lite/v4.json",
"data": {
"values": "<DVC_METRIC_DATA>"
},
"title": "<DVC_METRIC_TITLE>",
"width": 300,
"height": 300,
"layer": [
{
"encoding": {
"x": {
"field": "<DVC_METRIC_X>",
"type": "quantitative",
"title": "<DVC_METRIC_X_LABEL>"
},
"y": {
"field": "<DVC_METRIC_Y>",
"type": "quantitative",
"title": "<DVC_METRIC_Y_LABEL>",
"scale": {
"zero": false
}
},
"color": {
"field": "rev",
"type": "nominal"
}
},
"layer": [
{
"mark": "point"
},
{
"selection": {
"label": {
"type": "single",
"nearest": true,
"on": "mouseover",
"encodings": [
"x"
],
"empty": "none",
"clear": "mouseout"
}
},
"mark": "point",
"encoding": {
"opacity": {
"condition": {
"selection": "label",
"value": 1
},
"value": 0
}
}
}
]
},
{
"transform": [
{
"filter": {
"selection": "label"
}
}
],
"layer": [
{
"encoding": {
"text": {
"type": "quantitative",
"field": "<DVC_METRIC_Y>"
},
"x": {
"field": "<DVC_METRIC_X>",
"type": "quantitative"
},
"y": {
"field": "<DVC_METRIC_Y>",
"type": "quantitative"
}
},
"layer": [
{
"mark": {
"type": "text",
"align": "left",
"dx": 5,
"dy": -5
},
"encoding": {
"color": {
"type": "nominal",
"field": "rev"
}
}
}
]
}
]
}
]
}

39
.dvc/plots/smooth.json Normal file
View File

@ -0,0 +1,39 @@
{
"$schema": "https://vega.github.io/schema/vega-lite/v4.json",
"data": {
"values": "<DVC_METRIC_DATA>"
},
"title": "<DVC_METRIC_TITLE>",
"mark": {
"type": "line"
},
"encoding": {
"x": {
"field": "<DVC_METRIC_X>",
"type": "quantitative",
"title": "<DVC_METRIC_X_LABEL>"
},
"y": {
"field": "<DVC_METRIC_Y>",
"type": "quantitative",
"title": "<DVC_METRIC_Y_LABEL>",
"scale": {
"zero": false
}
},
"color": {
"field": "rev",
"type": "nominal"
}
},
"transform": [
{
"loess": "<DVC_METRIC_Y>",
"on": "<DVC_METRIC_X>",
"groupby": [
"rev"
],
"bandwidth": 0.3
}
]
}

3
.dvcignore Normal file
View File

@ -0,0 +1,3 @@
# Add patterns of files dvc should ignore, which could improve
# the performance. Learn more at
# https://dvc.org/doc/user-guide/dvcignore

3
.gitignore vendored Normal file
View File

@ -0,0 +1,3 @@
/train_dataset_dvc.csv
/test_dataset_dvc.csv
/logs_dvc.txt

View File

@ -58,4 +58,7 @@ test_dataset = pd.concat([X_test, y_test], axis=1)
train_dataset.to_csv('train_dataset.csv', index=False) train_dataset.to_csv('train_dataset.csv', index=False)
test_dataset.to_csv('test_dataset.csv', index=False) test_dataset.to_csv('test_dataset.csv', index=False)
train_dataset.to_csv('train_dataset_dvc.csv', index=False)
test_dataset.to_csv('test_dataset_dvc.csv', index=False)
print("Quiting create_data.py") print("Quiting create_data.py")

31
dvc.lock Normal file
View File

@ -0,0 +1,31 @@
schema: '2.0'
stages:
prepare:
cmd: python create_data.py
deps:
- path: KaggleV2-May-2016.csv
md5: cc55525de6e2b615aeba50095e8aaa95
size: 10850063
- path: create_data.py
md5: 0cefc3631ca8d15d62df548c92d53eb3
size: 2437
outs:
- path: test_dataset_dvc.csv
md5: b0d2e25243ff9f564546becf8464af55
size: 836063
- path: train_dataset_dvc.csv
md5: a17d28d659e1ba5f62a4203b7635ccfe
size: 3345298
train:
cmd: python train_model.py
deps:
- path: test_dataset_dvc.csv
md5: b0d2e25243ff9f564546becf8464af55
size: 836063
- path: train_dataset_dvc.csv
md5: a17d28d659e1ba5f62a4203b7635ccfe
size: 3345298
outs:
- path: logs_dvc.txt
md5: 506eda87493d4f7cc0ba2b7389b5a182
size: 52

16
dvc.yaml Normal file
View File

@ -0,0 +1,16 @@
stages:
prepare:
cmd: python create_data.py
deps:
- create_data.py
- KaggleV2-May-2016.csv
outs:
- train_dataset_dvc.csv
- test_dataset_dvc.csv
train:
cmd: python train_model.py
deps:
- train_dataset_dvc.csv
- test_dataset_dvc.csv
outs:
- logs_dvc.txt

View File

@ -1 +1,2 @@
loss=0.48354023694992065, accuracy=79.3711829902737 loss=0.48352938890457153, accuracy=79.37457588780819
loss=0.483554482460022, accuracy=79.36213526351504

View File

@ -6,8 +6,8 @@ import matplotlib
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import seaborn as sns import seaborn as sns
train_dataset = pd.read_csv('train_dataset.csv') train_dataset = pd.read_csv('train_dataset_dvc.csv')
test_dataset = pd.read_csv('test_dataset.csv') test_dataset = pd.read_csv('test_dataset_dvc.csv')
X_train = train_dataset.drop(columns=['No-show']).to_numpy() X_train = train_dataset.drop(columns=['No-show']).to_numpy()
X_test = test_dataset.drop(columns=['No-show']).to_numpy() X_test = test_dataset.drop(columns=['No-show']).to_numpy()
@ -80,3 +80,7 @@ print(f"Train - Loss: {loss.item()}. Accuracy: {accuracy}\n")
with open("logs.txt", "a") as myfile: with open("logs.txt", "a") as myfile:
myfile.write(f"loss={loss.item()}, accuracy={accuracy}\n") myfile.write(f"loss={loss.item()}, accuracy={accuracy}\n")
with open("logs_dvc.txt", "a") as myfile:
myfile.write(f"loss={loss.item()}, accuracy={accuracy}\n")