# EEG Analysis
This Library provides functions to process and plot EEG data, specifically focusing on the effects of different states (Before, During, After) on various EEG frequency bands.
## Installation
To install the library, use pip:
```bash
pip install eeg_analysis
```
## Usage
### Loading the Data
First, load the data from a CSV file. The CSV file should be structured with columns for subject, location, band, and power measurements for three states (Before, During, After).
```python
import pandas as pd
from eeg_analysis import load_data
# Load the data
data = load_data('path/to/your/data.csv')
```
### Cleaning the Data
Once the data is loaded, it needs to be cleaned and structured into a more usable format. The `clean_data` function organizes the data into a DataFrame with appropriate columns.
```python
from eeg_analysis import clean_data
# Clean and structure the data
df = clean_data(data)
# Optionally, save the cleaned data to a new CSV file
df.to_csv('cleaned_data.csv', index=False)
print(df.head())
```
### Performing Paired T-Tests
The library includes a function to perform paired t-tests between the different states for a specified frequency band. This can help determine if there are statistically significant differences in power between the states.
```python
from eeg_analysis import perform_ttests
# Perform t-tests for a specific band (e.g., 'Delta')
ttest_results_df = perform_ttests(df, 'Delta')
# Display the results
print(ttest_results_df)
```
### Plotting Median Power Across Bands
The library provides a function to plot the median power across different states for each frequency band. This can help visualize the changes in power for different subjects and states.
```python
from my_pypi_library import plot_median_across_bands
# Plot the median power across bands
plot_median_across_bands(df)
```
### Example Workflow
Here's a complete example that demonstrates the typical workflow using the library:
```python
import pandas as pd
from eeg_analysis import load_data, clean_data, perform_ttests, plot_median_across_bands
# Step 1: Load the data
data = load_data('path/to/your/data.csv')
# Step 2: Clean and structure the data
df = clean_data(data)
# Step 3: Perform t-tests for a specific band (e.g., 'Delta')
ttest_results_df = perform_ttests(df, 'Delta')
print(ttest_results_df)
# Step 4: Plot the median power across bands
plot_median_across_bands(df)
```
## API Reference
### `load_data(filepath: str) -> pd.DataFrame`
Load the data from a CSV file.
- **Parameters:**
- `filepath` (str): The path to the CSV file containing the data.
- **Returns:**
- `pd.DataFrame`: A DataFrame containing the loaded data.
### `clean_data(data: pd.DataFrame) -> pd.DataFrame`
Clean and structure the data into a usable format.
- **Parameters:**
- `data` (pd.DataFrame): The raw data DataFrame.
- **Returns:**
- `pd.DataFrame`: A cleaned and structured DataFrame.
### `perform_ttests(data: pd.DataFrame, band: str) -> pd.DataFrame`
Perform paired t-tests for a given frequency band.
- **Parameters:**
- `data` (pd.DataFrame): The cleaned data DataFrame.
- `band` (str): The frequency band to analyze (e.g., 'Delta').
- **Returns:**
- `pd.DataFrame`: A DataFrame containing the t-test results for each subject and comparison.
### `plot_median_across_bands(data: pd.DataFrame)`
Plot the median power across different states for each frequency band.
- **Parameters:**
- `data` (pd.DataFrame): The cleaned data DataFrame.
## Contributing
Contributions are welcome! If you find any bugs or have suggestions for improvements, please open an issue or submit a pull request on [GitHub](https://github.com/KarthikDani/BCI-Internship/tree/main/eeg_analysis).
## License
This project is licensed under the MIT License. See the [LICENSE](LICENSE.txt) file for details.
Raw data
{
"_id": null,
"home_page": "https://github.com/KarthikDani/PHCCOProject/tree/main/gsmm",
"name": "eeg-analysis",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": null,
"author": "Karthik Dani",
"author_email": "karthikdani14@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/1b/9b/39f1ca68c9ccb2671d44b95def1d907764d351950510fdbbdae2a1ddb62c/eeg_analysis-0.1.3.tar.gz",
"platform": null,
"description": "# EEG Analysis\n\nThis Library provides functions to process and plot EEG data, specifically focusing on the effects of different states (Before, During, After) on various EEG frequency bands.\n\n## Installation\n\nTo install the library, use pip:\n\n```bash\npip install eeg_analysis\n```\n\n## Usage\n\n### Loading the Data\n\nFirst, load the data from a CSV file. The CSV file should be structured with columns for subject, location, band, and power measurements for three states (Before, During, After).\n\n```python\nimport pandas as pd\nfrom eeg_analysis import load_data\n\n# Load the data\ndata = load_data('path/to/your/data.csv')\n```\n\n### Cleaning the Data\n\nOnce the data is loaded, it needs to be cleaned and structured into a more usable format. The `clean_data` function organizes the data into a DataFrame with appropriate columns.\n\n```python\nfrom eeg_analysis import clean_data\n\n# Clean and structure the data\ndf = clean_data(data)\n\n# Optionally, save the cleaned data to a new CSV file\ndf.to_csv('cleaned_data.csv', index=False)\nprint(df.head())\n```\n\n### Performing Paired T-Tests\n\nThe library includes a function to perform paired t-tests between the different states for a specified frequency band. This can help determine if there are statistically significant differences in power between the states.\n\n```python\nfrom eeg_analysis import perform_ttests\n\n# Perform t-tests for a specific band (e.g., 'Delta')\nttest_results_df = perform_ttests(df, 'Delta')\n\n# Display the results\nprint(ttest_results_df)\n```\n\n### Plotting Median Power Across Bands\n\nThe library provides a function to plot the median power across different states for each frequency band. This can help visualize the changes in power for different subjects and states.\n\n```python\nfrom my_pypi_library import plot_median_across_bands\n\n# Plot the median power across bands\nplot_median_across_bands(df)\n```\n\n### Example Workflow\n\nHere's a complete example that demonstrates the typical workflow using the library:\n\n```python\nimport pandas as pd\nfrom eeg_analysis import load_data, clean_data, perform_ttests, plot_median_across_bands\n\n# Step 1: Load the data\ndata = load_data('path/to/your/data.csv')\n\n# Step 2: Clean and structure the data\ndf = clean_data(data)\n\n# Step 3: Perform t-tests for a specific band (e.g., 'Delta')\nttest_results_df = perform_ttests(df, 'Delta')\nprint(ttest_results_df)\n\n# Step 4: Plot the median power across bands\nplot_median_across_bands(df)\n```\n\n## API Reference\n\n### `load_data(filepath: str) -> pd.DataFrame`\n\nLoad the data from a CSV file.\n\n- **Parameters:**\n - `filepath` (str): The path to the CSV file containing the data.\n\n- **Returns:**\n - `pd.DataFrame`: A DataFrame containing the loaded data.\n\n### `clean_data(data: pd.DataFrame) -> pd.DataFrame`\n\nClean and structure the data into a usable format.\n\n- **Parameters:**\n - `data` (pd.DataFrame): The raw data DataFrame.\n\n- **Returns:**\n - `pd.DataFrame`: A cleaned and structured DataFrame.\n\n### `perform_ttests(data: pd.DataFrame, band: str) -> pd.DataFrame`\n\nPerform paired t-tests for a given frequency band.\n\n- **Parameters:**\n - `data` (pd.DataFrame): The cleaned data DataFrame.\n - `band` (str): The frequency band to analyze (e.g., 'Delta').\n\n- **Returns:**\n - `pd.DataFrame`: A DataFrame containing the t-test results for each subject and comparison.\n\n### `plot_median_across_bands(data: pd.DataFrame)`\n\nPlot the median power across different states for each frequency band.\n\n- **Parameters:**\n - `data` (pd.DataFrame): The cleaned data DataFrame.\n\n## Contributing\n\nContributions are welcome! If you find any bugs or have suggestions for improvements, please open an issue or submit a pull request on [GitHub](https://github.com/KarthikDani/BCI-Internship/tree/main/eeg_analysis).\n\n## License\n\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE.txt) file for details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A library for processing and plotting EEG data",
"version": "0.1.3",
"project_urls": {
"Homepage": "https://github.com/KarthikDani/PHCCOProject/tree/main/gsmm"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "7d826b2ec6815cd6ffea6313aa8687716de83d41fd54fa5833d22719afac6aa2",
"md5": "3d92914da65f9e94f31e31e73460f778",
"sha256": "406a8df18c786a149d786be6e155f154e2f2a3c66b2c5b78ca97418abb151f2c"
},
"downloads": -1,
"filename": "eeg_analysis-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3d92914da65f9e94f31e31e73460f778",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 157759,
"upload_time": "2024-09-07T14:58:08",
"upload_time_iso_8601": "2024-09-07T14:58:08.703597Z",
"url": "https://files.pythonhosted.org/packages/7d/82/6b2ec6815cd6ffea6313aa8687716de83d41fd54fa5833d22719afac6aa2/eeg_analysis-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "1b9b39f1ca68c9ccb2671d44b95def1d907764d351950510fdbbdae2a1ddb62c",
"md5": "0cdd4066c3190e9001b0b28c75236512",
"sha256": "244cd3e766ea01c588b4630108925449079309338e73124fb52bddbb5e63abeb"
},
"downloads": -1,
"filename": "eeg_analysis-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "0cdd4066c3190e9001b0b28c75236512",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 157181,
"upload_time": "2024-09-07T14:58:12",
"upload_time_iso_8601": "2024-09-07T14:58:12.104399Z",
"url": "https://files.pythonhosted.org/packages/1b/9b/39f1ca68c9ccb2671d44b95def1d907764d351950510fdbbdae2a1ddb62c/eeg_analysis-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-07 14:58:12",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "KarthikDani",
"github_project": "PHCCOProject",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "eeg-analysis"
}
JSON
