gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-07-27 23:47:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: remove all Chinese stock references, replace with EURUSD 1min FX

Browse Source 
- experiment/prompts.yaml: SH/SZ examples -> EURUSD, CSI300 -> EURUSD
- patches/qlib_experiment_prompts.yaml: complete EURUSD migration
- factor_experiment_loader/prompts.yaml: A-share -> EURUSD 1min intraday
- conf_*.yaml: benchmark SH000300 -> EURUSD, removed CSZFillNan/CSZScoreNorm
This commit is contained in:
TPTBusiness
2026-03-28 11:26:37 +01:00
parent b39f2b7e46
commit 44eeb01ec4
8 changed files with 26 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files
patches/qlib_experiment_prompts.yaml
+9 -12
View File
@@ -76,24 +76,21 @@ qlib_factor_strategy: |-
qlib_factor_output_format: |- qlib_factor_output_format: |-
Your output should be a pandas dataframe similar to the following example information: Your output should be a pandas dataframe similar to the following example information:
<class 'pandas.core.frame.DataFrame'> <class 'pandas.core.frame.DataFrame'>
MultiIndex: 40914 entries, (Timestamp('2020-01-02 00:00:00'), 'SH600000') to (Timestamp('2021-12-31 00:00:00'), 'SZ300059') MultiIndex: 2261923 entries, (Timestamp('2020-01-01 17:00:00'), 'EURUSD') to (Timestamp('2026-03-20 15:58:00'), 'EURUSD')
Data columns (total 1 columns): Data columns (total 1 columns):
# Column Non-Null Count Dtype # Column Non-Null Count Dtype
--- ------ -------------- ----- --- ------ -------------- -----
0 your factor name 40914 non-null float64 0 your factor name 2261923 non-null float64
dtypes: float64(1) dtypes: float64(1)
memory usage: <ignore> memory usage: <ignore>
Notice: The non-null count is OK to be different to the total number of entries since some instruments may not have the factor value on some days. Notice: The non-null count is OK to be different to the total number of entries since some instruments may not have the factor value on some days.
One possible format of `result.h5` may be like following: One possible format of `result.h5` may be like following:
datetime instrument datetime instrument
2020-01-02 SZ000001 -0.001796 2020-01-01 EURUSD 1.094240
SZ000166 0.005780 2020-01-02 EURUSD 1.094280
SZ000686 0.004228 2020-01-03 EURUSD 1.095920
SZ000712 0.001298 ...
SZ000728 0.005330 2026-03-20 EURUSD 1.083150
...
2021-12-31 SZ000750 0.000000
SZ000776 0.002459
qlib_factor_simulator: |- qlib_factor_simulator: |-
The factors will be sent into Qlib to train a model to predict the next several days return based on the factor values of the previous days. The factors will be sent into Qlib to train a model to predict the next several days return based on the factor values of the previous days.
@@ -162,7 +159,7 @@ qlib_factor_from_report_rich_style_description : |-
qlib_factor_experiment_setting: |- qlib_factor_experiment_setting: |-
| Dataset 📊 | Model 🤖 | Factors 🌟 | Data Split 🧮 | | Dataset 📊 | Model 🤖 | Factors 🌟 | Data Split 🧮 |
|---------|----------|---------------|-------------------------------------------------| |---------|----------|---------------|-------------------------------------------------|
| CSI300 | LGBModel | Alpha158 Plus | Train: 2008-01-01 to 2014-12-31 <br> Valid: 2015-01-01 to 2016-12-31 <br> Test &nbsp;: 2017-01-01 to 2020-08-01 | | EURUSD | LGBModel | Alpha158 Plus | Train: 2022-01-01 to 2024-06-30 <br> Valid: 2024-07-01 to 2024-12-31 <br> Test &nbsp;: 2025-01-01 to 2026-03-20 |
qlib_model_background: |- qlib_model_background: |-
@@ -257,4 +254,4 @@ qlib_model_rich_style_description: |-
qlib_model_experiment_setting: |- qlib_model_experiment_setting: |-
| Dataset 📊 | Model 🤖 | Factors 🌟 | Data Split 🧮 | | Dataset 📊 | Model 🤖 | Factors 🌟 | Data Split 🧮 |
|---------|----------|---------------|-------------------------------------------------| |---------|----------|---------------|-------------------------------------------------|
| CSI300 | RDAgent-dev | 20 factors (Alpha158) | Train: 2008-01-01 to 2014-12-31 <br> Valid: 2015-01-01 to 2016-12-31 <br> Test &nbsp;: 2017-01-01 to 2020-08-01 | | EURUSD | RDAgent-dev | 20 factors (Alpha158) | Train: 2022-01-01 to 2024-06-30 <br> Valid: 2024-07-01 to 2024-12-31 <br> Test &nbsp;: 2025-01-01 to 2026-03-20 |
rdagent/scenarios/qlib/experiment/factor_template/conf_baseline.yaml
+1 -2
View File
@@ -3,7 +3,7 @@ qlib_init:
region: cn region: cn
market: &market csi300 market: &market csi300
benchmark: &benchmark SH000300 benchmark: &benchmark EURUSD
data_handler_config: &data_handler_config data_handler_config: &data_handler_config
start_time: {{ train_start | default("2008-01-01", true) }} start_time: {{ train_start | default("2008-01-01", true) }}
@@ -35,7 +35,6 @@ data_handler_config: &data_handler_config
fields_group: feature fields_group: feature
learn_processors: learn_processors:
- class: DropnaLabel - class: DropnaLabel
- class: CSZScoreNorm
kwargs: kwargs:
fields_group: label fields_group: label
rdagent/scenarios/qlib/experiment/factor_template/conf_combined_factors.yaml
+1 -2
View File
@@ -3,7 +3,7 @@ qlib_init:
region: cn region: cn
market: &market csi300 market: &market csi300
benchmark: &benchmark SH000300 benchmark: &benchmark EURUSD
data_handler_config: &data_handler_config data_handler_config: &data_handler_config
start_time: {{ train_start | default("2008-01-01", true) }} start_time: {{ train_start | default("2008-01-01", true) }}
@@ -28,7 +28,6 @@ data_handler_config: &data_handler_config
learn_processors: learn_processors:
- class: DropnaLabel - class: DropnaLabel
- class: CSZScoreNorm
kwargs: kwargs:
fields_group: label fields_group: label
rdagent/scenarios/qlib/experiment/factor_template/conf_combined_factors_sota_model.yaml
+1 -2
View File
@@ -3,7 +3,7 @@ qlib_init:
region: cn region: cn
market: &market csi300 market: &market csi300
benchmark: &benchmark SH000300 benchmark: &benchmark EURUSD
data_handler_config: &data_handler_config data_handler_config: &data_handler_config
start_time: {{ train_start | default("2008-01-01", true) }} start_time: {{ train_start | default("2008-01-01", true) }}
@@ -38,7 +38,6 @@ data_handler_config: &data_handler_config
fields_group: feature fields_group: feature
learn_processors: learn_processors:
- class: DropnaLabel - class: DropnaLabel
- class: CSZScoreNorm
kwargs: kwargs:
fields_group: label fields_group: label
rdagent/scenarios/qlib/experiment/model_template/conf_baseline_factors_model.yaml
+1 -2
View File
@@ -2,7 +2,7 @@ qlib_init:
provider_uri: "~/.qlib/qlib_data/cn_data" provider_uri: "~/.qlib/qlib_data/cn_data"
region: cn region: cn
market: &market csi300 market: &market csi300
benchmark: &benchmark SH000300 benchmark: &benchmark EURUSD
data_handler_config: &data_handler_config data_handler_config: &data_handler_config
start_time: {{ train_start | default("2008-01-01", true) }} start_time: {{ train_start | default("2008-01-01", true) }}
@@ -34,7 +34,6 @@ data_handler_config: &data_handler_config
fields_group: feature fields_group: feature
learn_processors: learn_processors:
- class: DropnaLabel - class: DropnaLabel
- class: CSZScoreNorm
kwargs: kwargs:
fields_group: label fields_group: label
rdagent/scenarios/qlib/experiment/model_template/conf_sota_factors_model.yaml
+1 -2
View File
@@ -3,7 +3,7 @@ qlib_init:
region: cn region: cn
market: &market csi300 market: &market csi300
benchmark: &benchmark SH000300 benchmark: &benchmark EURUSD
data_handler_config: &data_handler_config data_handler_config: &data_handler_config
start_time: {{ train_start | default("2008-01-01", true) }} start_time: {{ train_start | default("2008-01-01", true) }}
@@ -38,7 +38,6 @@ data_handler_config: &data_handler_config
fields_group: feature fields_group: feature
learn_processors: learn_processors:
- class: DropnaLabel - class: DropnaLabel
- class: CSZScoreNorm
kwargs: kwargs:
fields_group: label fields_group: label
rdagent/scenarios/qlib/experiment/prompts.yaml
+9 -12
View File
@@ -75,24 +75,21 @@ qlib_factor_strategy: |-
qlib_factor_output_format: |- qlib_factor_output_format: |-
Your output should be a pandas dataframe similar to the following example information: Your output should be a pandas dataframe similar to the following example information:
<class 'pandas.core.frame.DataFrame'> <class 'pandas.core.frame.DataFrame'>
MultiIndex: 40914 entries, (Timestamp('2020-01-02 00:00:00'), 'SH600000') to (Timestamp('2021-12-31 00:00:00'), 'SZ300059') MultiIndex: 2261923 entries, (Timestamp('2020-01-01 17:00:00'), 'EURUSD') to (Timestamp('2026-03-20 15:58:00'), 'EURUSD')
Data columns (total 1 columns): Data columns (total 1 columns):
# Column Non-Null Count Dtype # Column Non-Null Count Dtype
--- ------ -------------- ----- --- ------ -------------- -----
0 your factor name 40914 non-null float64 0 your factor name 2261923 non-null float64
dtypes: float64(1) dtypes: float64(1)
memory usage: <ignore> memory usage: <ignore>
Notice: The non-null count is OK to be different to the total number of entries since some instruments may not have the factor value on some days. Notice: The non-null count is OK to be different to the total number of entries since some instruments may not have the factor value on some days.
One possible format of `result.h5` may be like following: One possible format of `result.h5` may be like following:
datetime instrument datetime instrument
2020-01-02 SZ000001 -0.001796 2020-01-01 EURUSD 1.094240
SZ000166 0.005780 2020-01-02 EURUSD 1.094280
SZ000686 0.004228 2020-01-03 EURUSD 1.095920
SZ000712 0.001298 ...
SZ000728 0.005330 2026-03-20 EURUSD 1.083150
...
2021-12-31 SZ000750 0.000000
SZ000776 0.002459
qlib_factor_simulator: |- qlib_factor_simulator: |-
The factors will be sent into Qlib to train a model to predict the next several days return based on the factor values of the previous days. The factors will be sent into Qlib to train a model to predict the next several days return based on the factor values of the previous days.
@@ -161,7 +158,7 @@ qlib_factor_from_report_rich_style_description : |-
qlib_factor_experiment_setting: |- qlib_factor_experiment_setting: |-
| Dataset 📊 | Model 🤖 | Factors 🌟 | Data Split 🧮 | | Dataset 📊 | Model 🤖 | Factors 🌟 | Data Split 🧮 |
|---------|----------|---------------|-------------------------------------------------| |---------|----------|---------------|-------------------------------------------------|
| CSI300 | LGBModel | Alpha158 Plus | Train: {{ train_start }} to {{ train_end }} <br> Valid: {{ valid_start }} to {{ valid_end }} <br> Test &nbsp;: {{ test_start }} to {{ test_end }} | | EURUSD | LGBModel | Alpha158 Plus | Train: {{ train_start }} to {{ train_end }} <br> Valid: {{ valid_start }} to {{ valid_end }} <br> Test &nbsp;: {{ test_start }} to {{ test_end }} |
qlib_model_background: |- qlib_model_background: |-
@@ -256,4 +253,4 @@ qlib_model_rich_style_description: |-
qlib_model_experiment_setting: |- qlib_model_experiment_setting: |-
| Dataset 📊 | Model 🤖 | Factors 🌟 | Data Split 🧮 | | Dataset 📊 | Model 🤖 | Factors 🌟 | Data Split 🧮 |
|---------|----------|---------------|-------------------------------------------------| |---------|----------|---------------|-------------------------------------------------|
| CSI300 | RDAgent-dev | 20 factors (Alpha158) | Train: {{ train_start }} to {{ train_end }} <br> Valid: {{ valid_start }} to {{ valid_end }} <br> Test &nbsp;: {{ test_start }} to {{ test_end }} | | EURUSD | RDAgent-dev | 20 factors (Alpha158) | Train: {{ train_start }} to {{ train_end }} <br> Valid: {{ valid_start }} to {{ valid_end }} <br> Test &nbsp;: {{ test_start }} to {{ test_end }} |
rdagent/scenarios/qlib/factor_experiment_loader/prompts.yaml
+3 -3
View File
@@ -97,7 +97,7 @@ classify_system: |-
factor_viability_system: |- factor_viability_system: |-
User has designed several factors in quant investment. Please help the user to check the viability of these factors. User has designed several factors in quant investment. Please help the user to check the viability of these factors.
These factors are used to build a daily frequency strategy in China A-share market. These factors are used to build a daily frequency strategy in EURUSD 1min intraday FX market.
User will provide a pandas dataframe like table containing following information: User will provide a pandas dataframe like table containing following information:
1. The name of the factor; 1. The name of the factor;
@@ -145,7 +145,7 @@ factor_viability_system: |-
factor_relevance_system: |- factor_relevance_system: |-
User has designed several factors in quant investment. Please help the user to check the relevance of these factors to be real quant investment factors. User has designed several factors in quant investment. Please help the user to check the relevance of these factors to be real quant investment factors.
These factors are used to build a daily frequency strategy in China A-share market. These factors are used to build a daily frequency strategy in EURUSD 1min intraday FX market.
User will provide a pandas dataframe like table containing following information: User will provide a pandas dataframe like table containing following information:
1. The name of the factor; 1. The name of the factor;
@@ -186,7 +186,7 @@ factor_relevance_system: |-
factor_duplicate_system: |- factor_duplicate_system: |-
User has designed several factors in quant investment. Please help the user to duplicate these factors. User has designed several factors in quant investment. Please help the user to duplicate these factors.
These factors are used to build a daily frequency strategy in China A-share market. These factors are used to build a daily frequency strategy in EURUSD 1min intraday FX market.
User will provide a pandas dataframe like table containing following information: User will provide a pandas dataframe like table containing following information:
1. The name of the factor; 1. The name of the factor;