mirror of
https://github.com/newnius/YAO-optimizer.git
synced 2025-06-06 06:41:55 +00:00
update, add random forest
This commit is contained in:
parent
0c6f6eec11
commit
bf46dae01e
@ -3,7 +3,6 @@
|
||||
<component name="ChangeListManager">
|
||||
<list default="true" id="0aedafd8-e57e-462a-beda-65af0b91f3df" name="Default Changelist" comment="">
|
||||
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/README.md" beforeDir="false" afterPath="$PROJECT_DIR$/README.md" afterDir="false" />
|
||||
</list>
|
||||
<ignored path="$PROJECT_DIR$/out/" />
|
||||
<option name="EXCLUDED_CONVERTED_TO_IGNORED" value="true" />
|
||||
@ -16,10 +15,11 @@
|
||||
<session id="570274097">
|
||||
<usages-collector id="statistics.lifecycle.project">
|
||||
<counts>
|
||||
<entry key="project.closed" value="2" />
|
||||
<entry key="project.closed" value="3" />
|
||||
<entry key="project.open.time.1" value="3" />
|
||||
<entry key="project.open.time.2" value="1" />
|
||||
<entry key="project.open.time.3" value="1" />
|
||||
<entry key="project.opened" value="4" />
|
||||
<entry key="project.opened" value="5" />
|
||||
</counts>
|
||||
</usages-collector>
|
||||
<usages-collector id="statistics.file.extensions.open">
|
||||
@ -30,7 +30,7 @@
|
||||
<entry key="iml" value="1" />
|
||||
<entry key="md" value="2" />
|
||||
<entry key="png" value="7" />
|
||||
<entry key="py" value="7" />
|
||||
<entry key="py" value="11" />
|
||||
<entry key="sh" value="3" />
|
||||
<entry key="txt" value="2" />
|
||||
</counts>
|
||||
@ -43,7 +43,7 @@
|
||||
<entry key="Image" value="7" />
|
||||
<entry key="Markdown" value="2" />
|
||||
<entry key="PLAIN_TEXT" value="8" />
|
||||
<entry key="Python" value="7" />
|
||||
<entry key="Python" value="11" />
|
||||
</counts>
|
||||
</usages-collector>
|
||||
<usages-collector id="statistics.file.extensions.edit">
|
||||
@ -51,8 +51,8 @@
|
||||
<entry key="Dockerfile" value="81" />
|
||||
<entry key="csv" value="9" />
|
||||
<entry key="gitignore" value="12" />
|
||||
<entry key="md" value="232" />
|
||||
<entry key="py" value="4400" />
|
||||
<entry key="md" value="234" />
|
||||
<entry key="py" value="5489" />
|
||||
<entry key="sh" value="5" />
|
||||
</counts>
|
||||
</usages-collector>
|
||||
@ -60,100 +60,29 @@
|
||||
<counts>
|
||||
<entry key="Bash" value="5" />
|
||||
<entry key="Dockerfile" value="81" />
|
||||
<entry key="Markdown" value="232" />
|
||||
<entry key="Markdown" value="234" />
|
||||
<entry key="PLAIN_TEXT" value="21" />
|
||||
<entry key="Python" value="4400" />
|
||||
<entry key="Python" value="5489" />
|
||||
</counts>
|
||||
</usages-collector>
|
||||
</session>
|
||||
</component>
|
||||
<component name="FileEditorManager">
|
||||
<leaf SIDE_TABS_SIZE_LIMIT_KEY="300">
|
||||
<file pinned="false" current-in-tab="true">
|
||||
<entry file="file://$PROJECT_DIR$/serve_rf.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="165">
|
||||
<caret line="11" column="16" lean-forward="true" selection-start-line="11" selection-start-column="16" selection-end-line="11" selection-end-column="16" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="false">
|
||||
<entry file="file://$PROJECT_DIR$/main.py">
|
||||
<entry file="file://$PROJECT_DIR$/rf.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="90">
|
||||
<caret line="6" selection-start-line="6" selection-end-line="6" />
|
||||
<folding>
|
||||
<element signature="e#0#19#0" expanded="true" />
|
||||
</folding>
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="false">
|
||||
<entry file="file://$PROJECT_DIR$/.gitignore">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="30">
|
||||
<caret line="2" selection-start-line="2" selection-end-line="2" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="false">
|
||||
<entry file="file://$PROJECT_DIR$/serve.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="414">
|
||||
<caret line="211" column="31" selection-start-line="211" selection-start-column="31" selection-end-line="211" selection-end-column="31" />
|
||||
<folding>
|
||||
<element signature="e#18#46#0" expanded="true" />
|
||||
<marker date="1588426314177" expanded="true" signature="1271:1274" ph="..." />
|
||||
<marker date="1588426314177" expanded="true" signature="3519:3521" ph="..." />
|
||||
</folding>
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="false">
|
||||
<entry file="file://$PROJECT_DIR$/Dockerfile">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="255">
|
||||
<caret line="17" column="7" selection-start-line="17" selection-start-column="7" selection-end-line="17" selection-end-column="7" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="false">
|
||||
<entry file="file://$PROJECT_DIR$/train.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="960">
|
||||
<caret line="64" column="22" selection-start-line="64" selection-start-column="12" selection-end-line="64" selection-end-column="22" />
|
||||
<folding>
|
||||
<element signature="e#0#28#0" expanded="true" />
|
||||
</folding>
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="true">
|
||||
<entry file="file://$PROJECT_DIR$/README.md">
|
||||
<provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
|
||||
<state split_layout="SPLIT">
|
||||
<first_editor relative-caret-position="336">
|
||||
<caret line="31" column="26" selection-start-line="31" selection-start-column="26" selection-end-line="31" selection-end-column="26" />
|
||||
</first_editor>
|
||||
<second_editor />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="false">
|
||||
<entry file="file://$PROJECT_DIR$/bootstrap.sh">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="30">
|
||||
<caret line="2" column="22" selection-start-line="2" selection-start-column="22" selection-end-line="2" selection-end-column="22" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="false">
|
||||
<entry file="file://$PROJECT_DIR$/model_tensorflow.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="480">
|
||||
<caret line="32" column="58" selection-start-line="32" selection-start-column="58" selection-end-line="32" selection-end-column="58" />
|
||||
<folding>
|
||||
<element signature="e#0#23#0" expanded="true" />
|
||||
</folding>
|
||||
<caret line="7" column="36" lean-forward="true" selection-start-line="7" selection-start-column="36" selection-end-line="7" selection-end-column="36" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
@ -185,6 +114,10 @@
|
||||
<find>12</find>
|
||||
<find>32</find>
|
||||
<find>forecast_lstm</find>
|
||||
<find>csv</find>
|
||||
<find>joblib</find>
|
||||
<find>traceback</find>
|
||||
<find>models[job]</find>
|
||||
</findStrings>
|
||||
</component>
|
||||
<component name="Git.Settings">
|
||||
@ -204,8 +137,10 @@
|
||||
<option value="$PROJECT_DIR$/data/data2.csv" />
|
||||
<option value="$PROJECT_DIR$/data/data3.csv" />
|
||||
<option value="$PROJECT_DIR$/train.py" />
|
||||
<option value="$PROJECT_DIR$/serve.py" />
|
||||
<option value="$PROJECT_DIR$/README.md" />
|
||||
<option value="$PROJECT_DIR$/rf.py" />
|
||||
<option value="$PROJECT_DIR$/serve.py" />
|
||||
<option value="$PROJECT_DIR$/serve_rf.py" />
|
||||
</list>
|
||||
</option>
|
||||
</component>
|
||||
@ -225,6 +160,7 @@
|
||||
</navigator>
|
||||
<panes>
|
||||
<pane id="Scope" />
|
||||
<pane id="PackagesPane" />
|
||||
<pane id="AndroidView" />
|
||||
<pane id="ProjectPane">
|
||||
<subPane>
|
||||
@ -242,13 +178,12 @@
|
||||
<select />
|
||||
</subPane>
|
||||
</pane>
|
||||
<pane id="PackagesPane" />
|
||||
</panes>
|
||||
</component>
|
||||
<component name="PropertiesComponent">
|
||||
<property name="WebServerToolWindowFactoryState" value="false" />
|
||||
<property name="aspect.path.notification.shown" value="true" />
|
||||
<property name="com.android.tools.idea.instantapp.provision.ProvisionBeforeRunTaskProvider.myTimeStamp" value="1588422524280" />
|
||||
<property name="com.android.tools.idea.instantapp.provision.ProvisionBeforeRunTaskProvider.myTimeStamp" value="1593010427833" />
|
||||
<property name="go.gopath.indexing.explicitly.defined" value="true" />
|
||||
<property name="nodejs_interpreter_path.stuck_in_default_project" value="undefined stuck path" />
|
||||
<property name="nodejs_npm_path_reset_for_default_project" value="true" />
|
||||
@ -259,13 +194,13 @@
|
||||
<property name="settings.editor.selected.configurable" value="http.proxy" />
|
||||
</component>
|
||||
<component name="RecentsManager">
|
||||
<key name="CopyFile.RECENT_KEYS">
|
||||
<recent name="$PROJECT_DIR$" />
|
||||
</key>
|
||||
<key name="MoveFile.RECENT_KEYS">
|
||||
<recent name="$PROJECT_DIR$" />
|
||||
<recent name="$PROJECT_DIR$/model" />
|
||||
</key>
|
||||
<key name="CopyFile.RECENT_KEYS">
|
||||
<recent name="$PROJECT_DIR$" />
|
||||
</key>
|
||||
</component>
|
||||
<component name="RunDashboard">
|
||||
<option name="ruleStates">
|
||||
@ -292,12 +227,13 @@
|
||||
<workItem from="1588152880522" duration="16973000" />
|
||||
<workItem from="1588319878551" duration="41219000" />
|
||||
<workItem from="1588426002721" duration="336000" />
|
||||
<workItem from="1588427782140" duration="237000" />
|
||||
<workItem from="1588427782140" duration="326000" />
|
||||
<workItem from="1592809729651" duration="9303000" />
|
||||
</task>
|
||||
<servers />
|
||||
</component>
|
||||
<component name="TimeTrackingManager">
|
||||
<option name="totallyTimeSpent" value="58765000" />
|
||||
<option name="totallyTimeSpent" value="68157000" />
|
||||
</component>
|
||||
<component name="ToolWindowManager">
|
||||
<frame x="0" y="0" width="1280" height="800" extended-state="0" />
|
||||
@ -308,10 +244,10 @@
|
||||
<window_info id="Capture Tool" order="2" />
|
||||
<window_info id="Favorites" order="3" side_tool="true" />
|
||||
<window_info id="Image Layers" order="4" />
|
||||
<window_info content_ui="combo" id="Project" order="5" sideWeight="0.49898168" visible="true" weight="0.26171243" />
|
||||
<window_info active="true" content_ui="combo" id="Project" order="5" sideWeight="0.49898168" visible="true" weight="0.2657512" />
|
||||
<window_info id="Structure" order="6" sideWeight="0.50101835" side_tool="true" weight="0.24959612" />
|
||||
<window_info anchor="bottom" id="Version Control" order="0" />
|
||||
<window_info active="true" anchor="bottom" id="Terminal" order="1" visible="true" weight="0.32739726" />
|
||||
<window_info anchor="bottom" id="Terminal" order="1" visible="true" weight="0.32739726" />
|
||||
<window_info anchor="bottom" id="Event Log" order="2" side_tool="true" />
|
||||
<window_info anchor="bottom" id="Database Changes" order="3" show_stripe_button="false" />
|
||||
<window_info anchor="bottom" id="Docker" order="4" show_stripe_button="false" />
|
||||
@ -382,7 +318,7 @@
|
||||
</entry>
|
||||
<entry file="file://$PROJECT_DIR$/main.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="90">
|
||||
<state relative-caret-position="30">
|
||||
<caret line="6" selection-start-line="6" selection-end-line="6" />
|
||||
<folding>
|
||||
<element signature="e#0#19#0" expanded="true" />
|
||||
@ -406,7 +342,7 @@
|
||||
</entry>
|
||||
<entry file="file://$PROJECT_DIR$/train.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="960">
|
||||
<state relative-caret-position="810">
|
||||
<caret line="64" column="22" selection-start-line="64" selection-start-column="12" selection-end-line="64" selection-end-column="22" />
|
||||
<folding>
|
||||
<element signature="e#0#28#0" expanded="true" />
|
||||
@ -423,7 +359,7 @@
|
||||
</entry>
|
||||
<entry file="file://$PROJECT_DIR$/model_tensorflow.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="480">
|
||||
<state relative-caret-position="465">
|
||||
<caret line="32" column="58" selection-start-line="32" selection-start-column="58" selection-end-line="32" selection-end-column="58" />
|
||||
<folding>
|
||||
<element signature="e#0#23#0" expanded="true" />
|
||||
@ -431,25 +367,38 @@
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
<entry file="file://$PROJECT_DIR$/README.md">
|
||||
<provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
|
||||
<state split_layout="SPLIT">
|
||||
<first_editor relative-caret-position="480">
|
||||
<caret line="32" selection-start-line="32" selection-end-line="32" />
|
||||
</first_editor>
|
||||
<second_editor />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
<entry file="file://$PROJECT_DIR$/serve.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="414">
|
||||
<caret line="211" column="31" selection-start-line="211" selection-start-column="31" selection-end-line="211" selection-end-column="31" />
|
||||
<state relative-caret-position="210">
|
||||
<caret line="14" column="27" lean-forward="true" selection-start-line="14" selection-start-column="27" selection-end-line="14" selection-end-column="27" />
|
||||
<folding>
|
||||
<element signature="e#18#46#0" expanded="true" />
|
||||
<marker date="1588426314177" expanded="true" signature="1271:1274" ph="..." />
|
||||
<marker date="1588426314177" expanded="true" signature="3519:3521" ph="..." />
|
||||
</folding>
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
<entry file="file://$PROJECT_DIR$/README.md">
|
||||
<provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
|
||||
<state split_layout="SPLIT">
|
||||
<first_editor relative-caret-position="336">
|
||||
<caret line="31" column="26" selection-start-line="31" selection-start-column="26" selection-end-line="31" selection-end-column="26" />
|
||||
</first_editor>
|
||||
<second_editor />
|
||||
<entry file="file://$PROJECT_DIR$/rf.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="90">
|
||||
<caret line="7" column="36" lean-forward="true" selection-start-line="7" selection-start-column="36" selection-end-line="7" selection-end-column="36" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
<entry file="file://$PROJECT_DIR$/serve_rf.py">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="165">
|
||||
<caret line="11" column="16" lean-forward="true" selection-start-line="11" selection-start-column="16" selection-end-line="11" selection-end-column="16" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
|
||||
149
rf.py
Normal file
149
rf.py
Normal file
@ -0,0 +1,149 @@
|
||||
# _*_coding:utf-8_*_
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
|
||||
def load_data(trainfile, testfile):
|
||||
traindata = pd.read_csv(trainfile)
|
||||
testdata = pd.read_csv(testfile)
|
||||
feature_data = traindata.iloc[:, 1:-1]
|
||||
label_data = traindata.iloc[:, -1]
|
||||
test_feature = testdata.iloc[:, 1:]
|
||||
return feature_data, label_data, test_feature
|
||||
|
||||
|
||||
def random_forest_train(feature_data, label_data, test_feature, submitfile):
|
||||
from sklearn.ensemble import RandomForestRegressor
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.metrics import mean_squared_error
|
||||
|
||||
X_train, X_test, y_train, y_test = train_test_split(feature_data, label_data, test_size=0.01)
|
||||
params = {
|
||||
'n_estimators': 70,
|
||||
'max_depth': 13,
|
||||
'min_samples_split': 10,
|
||||
'min_samples_leaf': 5, # 10
|
||||
'max_features': 7
|
||||
}
|
||||
print(X_test)
|
||||
model = RandomForestRegressor(**params)
|
||||
model.fit(X_train, y_train)
|
||||
# 对测试集进行预测
|
||||
y_pred = model.predict(X_test)
|
||||
# 计算准确率
|
||||
MSE = mean_squared_error(y_test, y_pred)
|
||||
RMSE = np.sqrt(MSE)
|
||||
print(RMSE)
|
||||
|
||||
submit = pd.read_csv(submitfile)
|
||||
print(submit)
|
||||
print(model.predict(test_feature))
|
||||
submit['CPU'] = model.predict(test_feature)
|
||||
submit.to_csv('my_random_forest_prediction1.csv', index=False)
|
||||
print(submit)
|
||||
|
||||
|
||||
def random_forest_parameter_tuning1(feature_data, label_data, test_feature):
|
||||
from sklearn.ensemble import RandomForestRegressor
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.metrics import mean_squared_error
|
||||
from sklearn.model_selection import GridSearchCV
|
||||
|
||||
X_train, X_test, y_train, y_test = train_test_split(feature_data, label_data, test_size=0.23)
|
||||
param_test1 = {
|
||||
'n_estimators': range(10, 71, 10)
|
||||
}
|
||||
model = GridSearchCV(estimator=RandomForestRegressor(
|
||||
min_samples_split=100, min_samples_leaf=20, max_depth=8, max_features='sqrt',
|
||||
random_state=10), param_grid=param_test1, cv=5
|
||||
)
|
||||
model.fit(X_train, y_train)
|
||||
# 对测试集进行预测
|
||||
y_pred = model.predict(X_test)
|
||||
# 计算准确率
|
||||
MSE = mean_squared_error(y_test, y_pred)
|
||||
RMSE = np.sqrt(MSE)
|
||||
print(RMSE)
|
||||
return model.best_score_, model.best_params_
|
||||
|
||||
|
||||
def random_forest_parameter_tuning2(feature_data, label_data, test_feature):
|
||||
from sklearn.ensemble import RandomForestRegressor
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.metrics import mean_squared_error
|
||||
from sklearn.model_selection import GridSearchCV
|
||||
|
||||
X_train, X_test, y_train, y_test = train_test_split(feature_data, label_data, test_size=0.23)
|
||||
param_test2 = {
|
||||
'max_depth': range(3, 14, 2),
|
||||
'min_samples_split': range(50, 201, 20)
|
||||
}
|
||||
model = GridSearchCV(estimator=RandomForestRegressor(
|
||||
n_estimators=70, min_samples_leaf=20, max_features='sqrt', oob_score=True,
|
||||
random_state=10), param_grid=param_test2, cv=5
|
||||
)
|
||||
model.fit(X_train, y_train)
|
||||
# 对测试集进行预测
|
||||
y_pred = model.predict(X_test)
|
||||
# 计算准确率
|
||||
MSE = mean_squared_error(y_test, y_pred)
|
||||
RMSE = np.sqrt(MSE)
|
||||
print(RMSE)
|
||||
return model.best_score_, model.best_params_
|
||||
|
||||
|
||||
def random_forest_parameter_tuning3(feature_data, label_data, test_feature):
|
||||
from sklearn.ensemble import RandomForestRegressor
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.metrics import mean_squared_error
|
||||
from sklearn.model_selection import GridSearchCV
|
||||
|
||||
X_train, X_test, y_train, y_test = train_test_split(feature_data, label_data, test_size=0.23)
|
||||
param_test3 = {
|
||||
'min_samples_split': range(10, 90, 20),
|
||||
'min_samples_leaf': range(10, 60, 10),
|
||||
}
|
||||
model = GridSearchCV(estimator=RandomForestRegressor(
|
||||
n_estimators=70, max_depth=13, max_features='sqrt', oob_score=True,
|
||||
random_state=10), param_grid=param_test3, cv=5
|
||||
)
|
||||
model.fit(X_train, y_train)
|
||||
# 对测试集进行预测
|
||||
y_pred = model.predict(X_test)
|
||||
# 计算准确率
|
||||
MSE = mean_squared_error(y_test, y_pred)
|
||||
RMSE = np.sqrt(MSE)
|
||||
print(RMSE)
|
||||
return model.best_score_, model.best_params_
|
||||
|
||||
|
||||
def random_forest_parameter_tuning4(feature_data, label_data, test_feature):
|
||||
from sklearn.ensemble import RandomForestRegressor
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.metrics import mean_squared_error
|
||||
from sklearn.model_selection import GridSearchCV
|
||||
|
||||
X_train, X_test, y_train, y_test = train_test_split(feature_data, label_data, test_size=0.23)
|
||||
param_test4 = {
|
||||
'max_features': range(3, 9, 2)
|
||||
}
|
||||
model = GridSearchCV(estimator=RandomForestRegressor(
|
||||
n_estimators=70, max_depth=13, min_samples_split=10, min_samples_leaf=10, oob_score=True,
|
||||
random_state=10), param_grid=param_test4, cv=5
|
||||
)
|
||||
model.fit(X_train, y_train)
|
||||
# 对测试集进行预测
|
||||
y_pred = model.predict(X_test)
|
||||
# 计算准确率
|
||||
MSE = mean_squared_error(y_test, y_pred)
|
||||
RMSE = np.sqrt(MSE)
|
||||
print(RMSE)
|
||||
return model.best_score_, model.best_params_
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
trainfile = 'data/train.csv'
|
||||
testfile = 'data/test.csv'
|
||||
submitfile = 'data/sample_submit.csv'
|
||||
feature_data, label_data, test_feature = load_data(trainfile, testfile)
|
||||
random_forest_train(feature_data, label_data, test_feature, submitfile)
|
||||
272
serve.py
272
serve.py
@ -6,187 +6,106 @@ import cgi
|
||||
import json
|
||||
from urllib import parse
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
import csv
|
||||
from pandas import DataFrame
|
||||
from pandas import Series
|
||||
from pandas import concat
|
||||
from pandas import read_csv
|
||||
from sklearn.metrics import mean_squared_error
|
||||
from sklearn.preprocessing import MinMaxScaler
|
||||
from keras.models import Sequential
|
||||
from keras.layers import Dense
|
||||
from keras.layers import LSTM
|
||||
from math import sqrt
|
||||
import numpy
|
||||
import random
|
||||
import traceback
|
||||
from keras.models import load_model
|
||||
from sklearn.externals import joblib
|
||||
import pickle
|
||||
import os
|
||||
from sklearn.ensemble import RandomForestRegressor
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.metrics import mean_squared_error
|
||||
|
||||
PORT_NUMBER = 8080
|
||||
PORT_NUMBER = int(os.getenv('Port', 8080))
|
||||
lock = Lock()
|
||||
models = {}
|
||||
|
||||
|
||||
# frame a sequence as a supervised learning problem
|
||||
def timeseries_to_supervised(data, lag=1):
|
||||
df = DataFrame(data)
|
||||
columns = [df.shift(i) for i in range(1, lag + 1)]
|
||||
columns.append(df)
|
||||
df = concat(columns, axis=1)
|
||||
df = df.drop(0)
|
||||
return df
|
||||
|
||||
|
||||
# create a differenced series
|
||||
def difference(dataset, interval=1):
|
||||
diff = list()
|
||||
for i in range(interval, len(dataset)):
|
||||
value = dataset[i] - dataset[i - interval]
|
||||
diff.append(value)
|
||||
return Series(diff)
|
||||
|
||||
|
||||
# invert differenced value
|
||||
def inverse_difference(history, yhat, interval=1):
|
||||
return yhat + history[-interval]
|
||||
|
||||
|
||||
# inverse scaling for a forecasted value
|
||||
def invert_scale(scaler, X, yhat):
|
||||
new_row = [x for x in X] + [yhat]
|
||||
array = numpy.array(new_row)
|
||||
array = array.reshape(1, len(array))
|
||||
inverted = scaler.inverse_transform(array)
|
||||
return inverted[0, -1]
|
||||
|
||||
|
||||
# fit an LSTM network to training data
|
||||
def fit_lstm(train, batch_size2, nb_epoch, neurons):
|
||||
X, y = train[:, 0:-1], train[:, -1]
|
||||
X = X.reshape(X.shape[0], 1, X.shape[1])
|
||||
model = Sequential()
|
||||
model.add(LSTM(neurons, batch_input_shape=(batch_size2, X.shape[1], X.shape[2]), stateful=True))
|
||||
model.add(Dense(1))
|
||||
model.compile(loss='mean_squared_error', optimizer='adam')
|
||||
for i in range(nb_epoch):
|
||||
model.fit(X, y, epochs=1, batch_size=batch_size2, verbose=0, shuffle=False)
|
||||
# loss = model.evaluate(X, y)
|
||||
# print("Epoch {}/{}, loss = {}".format(i, nb_epoch, loss))
|
||||
print("Epoch {}/{}".format(i, nb_epoch))
|
||||
model.reset_states()
|
||||
return model
|
||||
def load_data(trainfile, testfile):
|
||||
traindata = pd.read_csv(trainfile)
|
||||
testdata = pd.read_csv(testfile)
|
||||
feature_data = traindata.iloc[:, 1:-1]
|
||||
label_data = traindata.iloc[:, -1]
|
||||
test_feature = testdata.iloc[:, 1:]
|
||||
return feature_data, label_data, test_feature
|
||||
|
||||
|
||||
def train_models(job):
|
||||
lock.acquire()
|
||||
if job not in models:
|
||||
models[job] = {
|
||||
'lock': Lock()
|
||||
}
|
||||
lock.release()
|
||||
|
||||
if job not in models or 'features' not in models[job]:
|
||||
return
|
||||
models[job]['lock'].acquire()
|
||||
|
||||
# load dataset
|
||||
series = read_csv('./data/' + job + '.csv', header=0, index_col=0, squeeze=True)
|
||||
for label in models[job]['labels']:
|
||||
trainfile = './data/' + job + '_' + label + '.csv'
|
||||
traindata = pd.read_csv(trainfile)
|
||||
feature_data = traindata.iloc[:, 1:-1]
|
||||
label_data = traindata.iloc[:, -1]
|
||||
|
||||
# transform data to be stationary
|
||||
raw_values = series.values
|
||||
diff_values = difference(raw_values, 1)
|
||||
# transform data to be supervised learning
|
||||
lag = 4
|
||||
supervised = timeseries_to_supervised(diff_values, lag)
|
||||
supervised_values = supervised.values
|
||||
X_train, X_test, y_train, y_test = train_test_split(feature_data, label_data, test_size=0.01)
|
||||
params = {
|
||||
'n_estimators': 70,
|
||||
'max_depth': 13,
|
||||
'min_samples_split': 10,
|
||||
'min_samples_leaf': 5, # 10
|
||||
'max_features': len(models[job]['features']) - 1 # 7
|
||||
}
|
||||
# print(params)
|
||||
model = RandomForestRegressor(**params)
|
||||
model.fit(X_train, y_train)
|
||||
|
||||
batch_size = 32
|
||||
if supervised_values.shape[0] < 100:
|
||||
batch_size = 16
|
||||
if supervised_values.shape[0] < 60:
|
||||
batch_size = 8
|
||||
# save the model to disk
|
||||
modelname = './data/' + job + '_' + label + '.sav'
|
||||
pickle.dump(model, open(modelname, 'wb'))
|
||||
|
||||
# split data into train and test-sets
|
||||
train = supervised_values
|
||||
# transform the scale of the data
|
||||
|
||||
# scale data to [-1, 1]
|
||||
# fit scaler
|
||||
scaler = MinMaxScaler(feature_range=(-1, 1))
|
||||
scaler = scaler.fit(train)
|
||||
# transform train
|
||||
train = train.reshape(train.shape[0], train.shape[1])
|
||||
train_scaled = scaler.transform(train)
|
||||
|
||||
# fit the model
|
||||
t1 = train.shape[0] % batch_size
|
||||
|
||||
train_trimmed = train_scaled[t1:, :]
|
||||
model = fit_lstm(train_trimmed, batch_size, 30, 4)
|
||||
|
||||
model.save('./data/checkpoint-' + job)
|
||||
scaler_filename = './data/checkpoint-' + job + "-scaler.save"
|
||||
joblib.dump(scaler, scaler_filename)
|
||||
|
||||
models[job]['batch_size'] = batch_size
|
||||
# 对测试集进行预测
|
||||
y_pred = model.predict(X_test)
|
||||
# 计算准确率
|
||||
MSE = mean_squared_error(y_test, y_pred)
|
||||
RMSE = np.sqrt(MSE)
|
||||
print('RMSE of ' + job + ' is ' + str(RMSE))
|
||||
|
||||
models[job]['lock'].release()
|
||||
|
||||
|
||||
def predict(job, seq):
|
||||
if job not in models or 'batch_size' not in models[job]:
|
||||
def predict(job, features):
|
||||
if job not in models or 'features' not in models[job]:
|
||||
return -1, False
|
||||
|
||||
batch_size = int(models[job]['batch_size'])
|
||||
values = [job]
|
||||
for feature in models[job]['features']:
|
||||
values.append(features[feature])
|
||||
|
||||
data = {
|
||||
'seq': seq,
|
||||
'value': 0,
|
||||
}
|
||||
model = load_model('./data/checkpoint-' + job)
|
||||
scaler_filename = './data/checkpoint-' + job + "-scaler.save"
|
||||
scaler = joblib.load(scaler_filename)
|
||||
datafile = './data/' + job + '.' + str(random.randint(1000, 9999)) + '.csv'
|
||||
t = ['job']
|
||||
t.extend(models[job]['features'])
|
||||
with open(datafile, 'w', newline='') as csvfile:
|
||||
spamwriter = csv.writer(
|
||||
csvfile, delimiter=',',
|
||||
quotechar='|', quoting=csv.QUOTE_MINIMAL
|
||||
)
|
||||
spamwriter.writerow(t)
|
||||
|
||||
file = './data/' + job + '.' + str(random.randint(1000, 9999)) + '.csv'
|
||||
df = pd.read_csv('./data/' + job + '.csv', usecols=['seq', 'value'])
|
||||
df = df.tail(batch_size * 2 - 1)
|
||||
df = df.append(data, ignore_index=True)
|
||||
df.to_csv(file, index=False)
|
||||
with open(datafile, 'a+', newline='') as csvfile:
|
||||
spamwriter = csv.writer(
|
||||
csvfile, delimiter=',',
|
||||
quotechar='|', quoting=csv.QUOTE_MINIMAL
|
||||
)
|
||||
spamwriter.writerow(values)
|
||||
|
||||
# load dataset
|
||||
df = read_csv(file, header=0, index_col=0, squeeze=True)
|
||||
testdata = pd.read_csv(datafile)
|
||||
test_feature = testdata.iloc[:, 1:]
|
||||
|
||||
# transform data to be stationary
|
||||
raw_values = df.values
|
||||
diff_values = difference(raw_values, 1)
|
||||
predictions = {}
|
||||
for label in models[job]['labels']:
|
||||
# load the model from disk
|
||||
modelfile = './data/' + job + '_' + label + '.sav'
|
||||
model = pickle.load(open(modelfile, 'rb'))
|
||||
preds = model.predict(test_feature)
|
||||
predictions[label] = preds[0]
|
||||
|
||||
# transform data to be supervised learning
|
||||
lag = 4
|
||||
supervised = timeseries_to_supervised(diff_values, lag)
|
||||
supervised_values = supervised[-batch_size:]
|
||||
test = supervised_values.values
|
||||
|
||||
test = test.reshape(test.shape[0], test.shape[1])
|
||||
test_scaled = scaler.transform(test)
|
||||
|
||||
# forecast the entire training dataset to build up state for forecasting
|
||||
test_reshaped = test_scaled[:, 0:-1]
|
||||
test_reshaped = test_reshaped.reshape(len(test_reshaped), 1, lag)
|
||||
output = model.predict(test_reshaped, batch_size=batch_size)
|
||||
predictions = list()
|
||||
for i in range(len(output)):
|
||||
yhat = output[i, 0]
|
||||
X = test_scaled[i, 0:-1]
|
||||
# invert scaling
|
||||
yhat = invert_scale(scaler, X, yhat)
|
||||
# invert differencing
|
||||
yhat = inverse_difference(raw_values, yhat, len(test_scaled) + 1 - i)
|
||||
# store forecast
|
||||
predictions.append(yhat)
|
||||
# report performance
|
||||
|
||||
rmse = sqrt(mean_squared_error(raw_values[-batch_size:], predictions))
|
||||
print(predictions, raw_values[-batch_size:])
|
||||
return predictions[-1], True
|
||||
if os.path.exists(datafile):
|
||||
os.remove(datafile)
|
||||
return predictions, True
|
||||
|
||||
|
||||
class MyHandler(BaseHTTPRequestHandler):
|
||||
@ -204,15 +123,15 @@ class MyHandler(BaseHTTPRequestHandler):
|
||||
elif req.path == "/predict":
|
||||
try:
|
||||
job = query.get('job')[0]
|
||||
seq = query.get('seq')[0]
|
||||
features = json.loads(query.get('features')[0])
|
||||
msg = {'code': 0, 'error': ""}
|
||||
|
||||
pred, success = predict(job, int(seq))
|
||||
pred, success = predict(job, features)
|
||||
|
||||
if not success:
|
||||
msg = {'code': 2, 'error': "Job " + job + " not exist"}
|
||||
else:
|
||||
msg = {'code': 0, 'error': "", "total": int(pred)}
|
||||
msg = {'code': 0, 'error': "", "labels": json.dumps(pred)}
|
||||
except Exception as e:
|
||||
track = traceback.format_exc()
|
||||
print(track)
|
||||
@ -226,26 +145,50 @@ class MyHandler(BaseHTTPRequestHandler):
|
||||
elif req.path == "/feed":
|
||||
try:
|
||||
job = query.get('job')[0]
|
||||
seq = query.get('seq')[0]
|
||||
value = query.get('value')[0]
|
||||
features = json.loads(query.get('features')[0])
|
||||
labels = json.loads(query.get('labels')[0])
|
||||
|
||||
if int(seq) == 1:
|
||||
with open('./data/' + job + '.csv', 'w', newline='') as csvfile:
|
||||
lock.acquire()
|
||||
flag = False
|
||||
if job not in models:
|
||||
models[job] = {
|
||||
'lock': Lock(),
|
||||
'features': list(features.keys()),
|
||||
'labels': list(labels.keys())
|
||||
}
|
||||
flag = True
|
||||
lock.release()
|
||||
models[job]['lock'].acquire()
|
||||
|
||||
for label in models[job]['labels']:
|
||||
values = [job]
|
||||
for feature in models[job]['features']:
|
||||
values.append(features[feature])
|
||||
values.append(labels[label])
|
||||
if flag:
|
||||
t = ['job']
|
||||
t.extend(models[job]['features'])
|
||||
t.append(label)
|
||||
with open('./data/' + job + '_' + label + '.csv', 'w', newline='') as csvfile:
|
||||
spamwriter = csv.writer(
|
||||
csvfile, delimiter=',',
|
||||
quotechar='|', quoting=csv.QUOTE_MINIMAL
|
||||
)
|
||||
spamwriter.writerow(["seq", "value"])
|
||||
spamwriter.writerow(t)
|
||||
|
||||
with open('./data/' + job + '.csv', 'a+', newline='') as csvfile:
|
||||
with open('./data/' + job + '_' + label + '.csv', 'a+', newline='') as csvfile:
|
||||
spamwriter = csv.writer(
|
||||
csvfile, delimiter=',',
|
||||
quotechar='|', quoting=csv.QUOTE_MINIMAL
|
||||
)
|
||||
spamwriter.writerow([seq, value])
|
||||
spamwriter.writerow(values)
|
||||
|
||||
models[job]['lock'].release()
|
||||
msg = {'code': 0, 'error': ""}
|
||||
except Exception as e:
|
||||
msg = {'code': 1, 'error': str(e)}
|
||||
track = traceback.format_exc()
|
||||
print(track)
|
||||
self.send_response(200)
|
||||
self.send_header('Content-type', 'application/json')
|
||||
self.end_headers()
|
||||
@ -289,7 +232,6 @@ class MyHandler(BaseHTTPRequestHandler):
|
||||
self.send_header('Content-type', 'application/json')
|
||||
self.end_headers()
|
||||
self.wfile.write(bytes(json.dumps(msg), "utf-8"))
|
||||
|
||||
else:
|
||||
self.send_error(404, 'File Not Found: %s' % self.path)
|
||||
|
||||
|
||||
310
serve_lstm.py
Normal file
310
serve_lstm.py
Normal file
@ -0,0 +1,310 @@
|
||||
#!/usr/bin/python
|
||||
from threading import Thread
|
||||
from threading import Lock
|
||||
from http.server import BaseHTTPRequestHandler, HTTPServer
|
||||
import cgi
|
||||
import json
|
||||
from urllib import parse
|
||||
import pandas as pd
|
||||
import csv
|
||||
from pandas import DataFrame
|
||||
from pandas import Series
|
||||
from pandas import concat
|
||||
from pandas import read_csv
|
||||
from sklearn.metrics import mean_squared_error
|
||||
from sklearn.preprocessing import MinMaxScaler
|
||||
from keras.models import Sequential
|
||||
from keras.layers import Dense
|
||||
from keras.layers import LSTM
|
||||
from math import sqrt
|
||||
import numpy
|
||||
import random
|
||||
import traceback
|
||||
from keras.models import load_model
|
||||
from sklearn.externals import joblib
|
||||
|
||||
PORT_NUMBER = 8080
|
||||
lock = Lock()
|
||||
models = {}
|
||||
|
||||
|
||||
# frame a sequence as a supervised learning problem
|
||||
def timeseries_to_supervised(data, lag=1):
|
||||
df = DataFrame(data)
|
||||
columns = [df.shift(i) for i in range(1, lag + 1)]
|
||||
columns.append(df)
|
||||
df = concat(columns, axis=1)
|
||||
df = df.drop(0)
|
||||
return df
|
||||
|
||||
|
||||
# create a differenced series
|
||||
def difference(dataset, interval=1):
|
||||
diff = list()
|
||||
for i in range(interval, len(dataset)):
|
||||
value = dataset[i] - dataset[i - interval]
|
||||
diff.append(value)
|
||||
return Series(diff)
|
||||
|
||||
|
||||
# invert differenced value
|
||||
def inverse_difference(history, yhat, interval=1):
|
||||
return yhat + history[-interval]
|
||||
|
||||
|
||||
# inverse scaling for a forecasted value
|
||||
def invert_scale(scaler, X, yhat):
|
||||
new_row = [x for x in X] + [yhat]
|
||||
array = numpy.array(new_row)
|
||||
array = array.reshape(1, len(array))
|
||||
inverted = scaler.inverse_transform(array)
|
||||
return inverted[0, -1]
|
||||
|
||||
|
||||
# fit an LSTM network to training data
|
||||
def fit_lstm(train, batch_size2, nb_epoch, neurons):
|
||||
X, y = train[:, 0:-1], train[:, -1]
|
||||
X = X.reshape(X.shape[0], 1, X.shape[1])
|
||||
model = Sequential()
|
||||
model.add(LSTM(neurons, batch_input_shape=(batch_size2, X.shape[1], X.shape[2]), stateful=True))
|
||||
model.add(Dense(1))
|
||||
model.compile(loss='mean_squared_error', optimizer='adam')
|
||||
for i in range(nb_epoch):
|
||||
model.fit(X, y, epochs=1, batch_size=batch_size2, verbose=0, shuffle=False)
|
||||
# loss = model.evaluate(X, y)
|
||||
# print("Epoch {}/{}, loss = {}".format(i, nb_epoch, loss))
|
||||
print("Epoch {}/{}".format(i, nb_epoch))
|
||||
model.reset_states()
|
||||
return model
|
||||
|
||||
|
||||
def train_models(job):
|
||||
lock.acquire()
|
||||
if job not in models:
|
||||
models[job] = {
|
||||
'lock': Lock()
|
||||
}
|
||||
lock.release()
|
||||
|
||||
models[job]['lock'].acquire()
|
||||
|
||||
# load dataset
|
||||
series = read_csv('./data/' + job + '.csv', header=0, index_col=0, squeeze=True)
|
||||
|
||||
# transform data to be stationary
|
||||
raw_values = series.values
|
||||
diff_values = difference(raw_values, 1)
|
||||
# transform data to be supervised learning
|
||||
lag = 4
|
||||
supervised = timeseries_to_supervised(diff_values, lag)
|
||||
supervised_values = supervised.values
|
||||
|
||||
batch_size = 32
|
||||
if supervised_values.shape[0] < 100:
|
||||
batch_size = 16
|
||||
if supervised_values.shape[0] < 60:
|
||||
batch_size = 8
|
||||
|
||||
# split data into train and test-sets
|
||||
train = supervised_values
|
||||
# transform the scale of the data
|
||||
|
||||
# scale data to [-1, 1]
|
||||
# fit scaler
|
||||
scaler = MinMaxScaler(feature_range=(-1, 1))
|
||||
scaler = scaler.fit(train)
|
||||
# transform train
|
||||
train = train.reshape(train.shape[0], train.shape[1])
|
||||
train_scaled = scaler.transform(train)
|
||||
|
||||
# fit the model
|
||||
t1 = train.shape[0] % batch_size
|
||||
|
||||
train_trimmed = train_scaled[t1:, :]
|
||||
model = fit_lstm(train_trimmed, batch_size, 30, 4)
|
||||
|
||||
model.save('./data/checkpoint-' + job)
|
||||
scaler_filename = './data/checkpoint-' + job + "-scaler.save"
|
||||
joblib.dump(scaler, scaler_filename)
|
||||
|
||||
models[job]['batch_size'] = batch_size
|
||||
|
||||
models[job]['lock'].release()
|
||||
|
||||
|
||||
def predict(job, seq):
|
||||
if job not in models or 'batch_size' not in models[job]:
|
||||
return -1, False
|
||||
|
||||
batch_size = int(models[job]['batch_size'])
|
||||
|
||||
data = {
|
||||
'seq': seq,
|
||||
'value': 0,
|
||||
}
|
||||
model = load_model('./data/checkpoint-' + job)
|
||||
scaler_filename = './data/checkpoint-' + job + "-scaler.save"
|
||||
scaler = joblib.load(scaler_filename)
|
||||
|
||||
file = './data/' + job + '.' + str(random.randint(1000, 9999)) + '.csv'
|
||||
df = pd.read_csv('./data/' + job + '.csv', usecols=['seq', 'value'])
|
||||
df = df.tail(batch_size * 2 - 1)
|
||||
df = df.append(data, ignore_index=True)
|
||||
df.to_csv(file, index=False)
|
||||
|
||||
# load dataset
|
||||
df = read_csv(file, header=0, index_col=0, squeeze=True)
|
||||
|
||||
# transform data to be stationary
|
||||
raw_values = df.values
|
||||
diff_values = difference(raw_values, 1)
|
||||
|
||||
# transform data to be supervised learning
|
||||
lag = 4
|
||||
supervised = timeseries_to_supervised(diff_values, lag)
|
||||
supervised_values = supervised[-batch_size:]
|
||||
test = supervised_values.values
|
||||
|
||||
test = test.reshape(test.shape[0], test.shape[1])
|
||||
test_scaled = scaler.transform(test)
|
||||
|
||||
# forecast the entire training dataset to build up state for forecasting
|
||||
test_reshaped = test_scaled[:, 0:-1]
|
||||
test_reshaped = test_reshaped.reshape(len(test_reshaped), 1, lag)
|
||||
output = model.predict(test_reshaped, batch_size=batch_size)
|
||||
predictions = list()
|
||||
for i in range(len(output)):
|
||||
yhat = output[i, 0]
|
||||
X = test_scaled[i, 0:-1]
|
||||
# invert scaling
|
||||
yhat = invert_scale(scaler, X, yhat)
|
||||
# invert differencing
|
||||
yhat = inverse_difference(raw_values, yhat, len(test_scaled) + 1 - i)
|
||||
# store forecast
|
||||
predictions.append(yhat)
|
||||
# report performance
|
||||
|
||||
rmse = sqrt(mean_squared_error(raw_values[-batch_size:], predictions))
|
||||
print(predictions, raw_values[-batch_size:])
|
||||
return predictions[-1], True
|
||||
|
||||
|
||||
class MyHandler(BaseHTTPRequestHandler):
|
||||
# Handler for the GET requests
|
||||
def do_GET(self):
|
||||
req = parse.urlparse(self.path)
|
||||
query = parse.parse_qs(req.query)
|
||||
|
||||
if req.path == "/ping":
|
||||
self.send_response(200)
|
||||
self.send_header('Content-type', 'application/json')
|
||||
self.end_headers()
|
||||
self.wfile.write(bytes("pong", "utf-8"))
|
||||
|
||||
elif req.path == "/predict":
|
||||
try:
|
||||
job = query.get('job')[0]
|
||||
seq = query.get('seq')[0]
|
||||
msg = {'code': 0, 'error': ""}
|
||||
|
||||
pred, success = predict(job, int(seq))
|
||||
|
||||
if not success:
|
||||
msg = {'code': 2, 'error': "Job " + job + " not exist"}
|
||||
else:
|
||||
msg = {'code': 0, 'error': "", "total": int(pred)}
|
||||
except Exception as e:
|
||||
track = traceback.format_exc()
|
||||
print(track)
|
||||
msg = {'code': 1, 'error': str(e)}
|
||||
|
||||
self.send_response(200)
|
||||
self.send_header('Content-type', 'application/json')
|
||||
self.end_headers()
|
||||
self.wfile.write(bytes(json.dumps(msg), "utf-8"))
|
||||
|
||||
elif req.path == "/feed":
|
||||
try:
|
||||
job = query.get('job')[0]
|
||||
seq = query.get('seq')[0]
|
||||
value = query.get('value')[0]
|
||||
|
||||
if int(seq) == 1:
|
||||
with open('./data/' + job + '.csv', 'w', newline='') as csvfile:
|
||||
spamwriter = csv.writer(
|
||||
csvfile, delimiter=',',
|
||||
quotechar='|', quoting=csv.QUOTE_MINIMAL
|
||||
)
|
||||
spamwriter.writerow(["seq", "value"])
|
||||
|
||||
with open('./data/' + job + '.csv', 'a+', newline='') as csvfile:
|
||||
spamwriter = csv.writer(
|
||||
csvfile, delimiter=',',
|
||||
quotechar='|', quoting=csv.QUOTE_MINIMAL
|
||||
)
|
||||
spamwriter.writerow([seq, value])
|
||||
msg = {'code': 0, 'error': ""}
|
||||
except Exception as e:
|
||||
msg = {'code': 1, 'error': str(e)}
|
||||
self.send_response(200)
|
||||
self.send_header('Content-type', 'application/json')
|
||||
self.end_headers()
|
||||
self.wfile.write(bytes(json.dumps(msg), "utf-8"))
|
||||
|
||||
elif req.path == "/train":
|
||||
try:
|
||||
job = query.get('job')[0]
|
||||
t = Thread(target=train_models, name='train_models', args=(job,))
|
||||
t.start()
|
||||
msg = {'code': 0, 'error': ""}
|
||||
except Exception as e:
|
||||
msg = {'code': 1, 'error': str(e)}
|
||||
self.send_response(200)
|
||||
self.send_header('Content-type', 'application/json')
|
||||
self.end_headers()
|
||||
self.wfile.write(bytes(json.dumps(msg), "utf-8"))
|
||||
|
||||
else:
|
||||
self.send_error(404, 'File Not Found: %s' % self.path)
|
||||
|
||||
# Handler for the POST requests
|
||||
def do_POST(self):
|
||||
if self.path == "/train2":
|
||||
form = cgi.FieldStorage(
|
||||
fp=self.rfile,
|
||||
headers=self.headers,
|
||||
environ={
|
||||
'REQUEST_METHOD': 'POST',
|
||||
'CONTENT_TYPE': self.headers['Content-Type'],
|
||||
})
|
||||
try:
|
||||
job = form.getvalue('job')[0]
|
||||
seq = form.getvalue('seq')[0]
|
||||
t = Thread(target=train_models(), name='train_models', args=(job, seq,))
|
||||
t.start()
|
||||
msg = {"code": 0, "error": ""}
|
||||
except Exception as e:
|
||||
msg = {"code": 1, "error": str(e)}
|
||||
self.send_response(200)
|
||||
self.send_header('Content-type', 'application/json')
|
||||
self.end_headers()
|
||||
self.wfile.write(bytes(json.dumps(msg), "utf-8"))
|
||||
|
||||
else:
|
||||
self.send_error(404, 'File Not Found: %s' % self.path)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
try:
|
||||
# Create a web server and define the handler to manage the
|
||||
# incoming request
|
||||
server = HTTPServer(('', PORT_NUMBER), MyHandler)
|
||||
print('Started http server on port ', PORT_NUMBER)
|
||||
|
||||
# Wait forever for incoming http requests
|
||||
server.serve_forever()
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print('^C received, shutting down the web server')
|
||||
|
||||
server.socket.close()
|
||||
Loading…
Reference in New Issue
Block a user