--- title: "AI Deploy - Tutorial - Deploy an interactive app for EDA and prediction using Streamlit" description: "Learn how to deploy an application for Exploratory Data Analysis (EDA) and interactive prediction." url: https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/ai-deploy-streamlit-eda-iris lang: en --- > For AI agents: the complete documentation index is available at https://docs.us.ovhcloud.com/en/llms.txt, the full documentation bundle is available at https://docs.us.ovhcloud.com/en/llms-full.txt. # AI Deploy - Tutorial - Deploy an interactive app for EDA and prediction using Streamlit **Learn how to deploy an application for Exploratory Data Analysis (EDA) and interactive prediction.** **Note:** AI Deploy is covered by **[OVHcloud Public Cloud Special Conditions](https://us.ovhcloud.com/legal/service-specific-terms/)**. The use case is the [IRIS dataset](https://en.wikipedia.org/wiki/Iris_flower_data_set). It is a collection of data containing information on **50 observations** of four different variables: `petal length`, `petal width`, `sepal length`, and `sepal width`. The first objective is to perform data mining on the source data from the **Iris dataset**. Then, the goal is to make predictions using a trained model. We will therefore use a neural network and weights from this [notebook](https://github.com/ovh/ai-training-examples/blob/main/notebooks/getting-started/pytorch/notebook_classification_iris.ipynb) to classify iris flowers between different species (`Setosa`, `Versicolor`, and `Virginica`). The four features are sent as input to the neural network. The **PyTorch model** will be loaded and run, and the prediction probabilities for each class will be extracted. Depending on the input data, it will be possible to visualize the corresponding iris on a **PCA plot** to compare the input to other data points in our Iris dataset. To do this, you will use [Streamlit](https://streamlit.io/), a Python framework that turns scripts into a shareable web application. You will also learn how to build and use a custom Docker image for a Streamlit application.   ## Requirements - Access to the [OVHcloud Control Panel](https://manager.us.ovhcloud.com/) - An AI Deploy project created inside a [Public Cloud project](https://us.ovhcloud.com/public-cloud/) in your OVHcloud account - A [user for AI Deploy](https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/manage-users-roles.md) - [Docker](https://www.docker.com/get-started) installed on your local computer - Some knowledge about building image and [Dockerfile](https://docs.docker.com/engine/reference/builder/) - You also should have followed **Step 6** of the _Classification of iris varieties within the same species_ notebook from the [GitHub repository](https://github.com/ovh/ai-training-examples/blob/main/notebooks/getting-started/pytorch/notebook_classification_iris.ipynb). You will be able to save your PyTorch model `model_iris_classification.pth`.   ## Instructions You are going to follow different steps to build your Streamlit application. - More information about Streamlit's capabilities can be found [here](https://docs.streamlit.io/en/stable/). - A direct link to the full Python file can be found [here](https://github.com/ovh/ai-training-examples/blob/main/apps/streamlit/eda-classification-iris/app.py). Here we will mainly discuss how to write the `utils.py` and `app.py` codes, the `requirements.txt` file, and the `Dockerfile`. If you want to see the whole code, please refer to the [GitHub repository](https://github.com/ovh/ai-training-examples/tree/main/apps/streamlit/eda-classification-iris).   ### Create the Streamlit application Two Python files are created to load the PyTorch model and build the Streamlit app.   #### Define the utils.py file This Python file is dedicated to loading the **PyTorch model**. You can find the full code [here](https://github.com/ovh/ai-training-examples/blob/main/apps/streamlit/eda-classification-iris/utils.py). First, we have to define the `Model` class with neural network architecture. ```python class Model(nn.Module): def __init__(self): super().__init__() # fully connected layer : 4 input features for 4 parameters in X self.layer1 = nn.Linear(in_features=4, out_features=16) # fully connected layer self.layer2 = nn.Linear(in_features=16, out_features=12) # output layer : 3 output features for 3 species self.output = nn.Linear(in_features=12, out_features=3) def forward(self, x): # activation fonction : reLU x = F.relu(self.layer1(x)) x = F.relu(self.layer2(x)) x = self.output(x) return x ``` Then, we create the function to load the model checkpoint. ```python def load_checkpoint(path): model = Model() print("Model display: ", model) model.load_state_dict(torch.load(path)) model.eval() return model ``` The last function allows us to load the model and get predictions. **Note:** To learn more about how you can save a model with PyTorch, please refer to the **last step** _"Save the model for future inference"_ of the [notebook](https://github.com/ovh/ai-training-examples/blob/main/notebooks/getting-started/pytorch/notebook_classification_iris.ipynb). **Note:** You can find the PyTorch model `model_iris_classification.pth` on the [GitHub repository](https://github.com/ovh/ai-training-examples/tree/main/apps/streamlit/eda-classification-iris). ```python def load_model(X_tensor): model = load_checkpoint(path) predict_out = model(X_tensor) _, predict_y = torch.max(predict_out, 1) return predict_out.squeeze().detach().numpy(), predict_y.item() # pytorch model path = "model_iris_classification.pth" ```   #### Write the app.py file Load the IRIS dataset for EDA. ```python @st.cache def load_data(): # load the iris dataset with sklearn dataset_iris = load_iris() # define inputs and output df_inputs = pd.DataFrame(dataset_iris.data, columns=dataset_iris.feature_names) df_output = pd.DataFrame(dataset_iris.target, columns=['variety']) return df_inputs, df_output ``` Display EDA figure based on source dataset. ```python @st.cache(allow_output_mutation=True) def data_visualization(df_inputs, df_output): df = pd.concat([df_inputs, df_output['variety']], axis=1) eda = sns.pairplot(data=df, hue="variety", palette=['#0D0888', '#CB4779', '#F0F922']) return eda ``` Create a sidebar with sliders. ```python def create_slider(df_inputs): # slidebars with min, max and mean (by default) values sepal_length = st.sidebar.slider( label='Sepal Length', min_value=float(df_inputs['sepal length (cm)'].min()), max_value=float(df_inputs['sepal length (cm)'].max()), value=float(round(df_inputs['sepal length (cm)'].mean(), 1)), step=0.1) sepal_width = st.sidebar.slider( label='Sepal Width', min_value=float(df_inputs['sepal width (cm)'].min()), max_value=float(df_inputs['sepal width (cm)'].max()), value=float(round(df_inputs['sepal width (cm)'].mean(), 1)), step=0.1) petal_length = st.sidebar.slider( label='Petal Length', min_value=float(df_inputs['petal length (cm)'].min()), max_value=float(df_inputs['petal length (cm)'].max()), value=float(round(df_inputs['petal length (cm)'].mean(), 1)), step=0.1) petal_width = st.sidebar.slider( label='Petal Width', min_value=float(df_inputs['petal width (cm)'].min()), max_value=float(df_inputs['petal width (cm)'].max()), value=float(round(df_inputs['petal width (cm)'].mean(), 1)), step=0.1) return sepal_length, sepal_width, petal_length, petal_width ``` Run a PCA. ```python @st.cache def run_pca(): pca = PCA(2) X = df_inputs.iloc[:, :4] X_pca = pca.fit_transform(X) df_pca = pd.DataFrame(pca.transform(X)) df_pca.columns = ['PC1', 'PC2'] df_pca = pd.concat([df_pca, df_output['variety']], axis=1) return pca, df_pca ``` Create a function that filters out negative values from the dataframe. Only positive values in the dataframe are kept. If a value is negative, it is set to zero. ```python def extract_positive_value(prediction): # f(prediction) = max(0, prediction) prediction_positive = [] for p in prediction: if p < 0: p = 0 prediction_positive.append(p) return pd.DataFrame({'Species': ['Setosa', 'Versicolor', 'Virginica'], 'Confidence': prediction_positive}) ``` Define a Python function to display the image according to Iris species. ```python def display_img(species): # define the list of images list_img = ['setosa.png', 'versicolor.png', 'virginica.png'] return Image.open(list_img[species]) ``` **Note:** All the functions defined above are called in the `main` Python file `app.py` to build the Streamlit app. You can find this part of the code as well as the different functions defined previously on the [GitHub repository](https://github.com/ovh/ai-training-examples/blob/main/apps/streamlit/eda-classification-iris/app.py).   ### Write the requirements.txt file for the application The `requirements.txt` file will allow us to write all the modules needed to make our application work. This file will be useful when writing the `Dockerfile`. ```console pandas==1.4.4 numpy==1.23.2 torch==1.12.1 streamlit==1.12.2 scikit-learn==1.1.2 plotly==5.10.0 Pillow==9.2.0 seaborn==0.12.0 altair==4.2.2 ```   ### Write the Dockerfile for the application Your Dockerfile should start with the `FROM` instruction indicating the parent image to use. In our case we choose to start from the `python:3.8` OVHcloud image: ```console python:3.8 ``` Create the home directory and add your files to it: ```console WORKDIR /workspace ADD . /workspace ``` Install the `requirements.txt` file which contains your needed Python modules using a `pip install ...` command: ```console RUN pip install -r requirements.txt ``` Define your default launching command to start the application: ```console CMD [ "streamlit", "run", "/workspace/app.py", "--server.address=0.0.0.0" ] ``` Give correct access rights to **ovhcloud user** (`42420:42420`): ```console RUN chown -R 42420:42420 /workspace ENV HOME=/workspace ```   ### Build the Docker image from the Dockerfile From the directory containing your **Dockerfile**, run one of the following commands to build your application image: ```console # Build the image using your machine's default architecture docker build . -t streamlit-eda-iris:latest # Build image targeting the linux/amd64 architecture docker buildx build --platform linux/amd64 -t streamlit-eda-iris:latest . ``` - The **first command** builds the image using your system’s default architecture. This may work if your machine already uses the `linux/amd64` architecture, which is required to run containers with our AI products. However, on systems with a different architecture (e.g. `ARM64` on `Apple Silicon`), the resulting image will not be compatible and cannot be deployed. - The **second command** explicitly targets the `linux/AMD64` architecture to ensure compatibility with our AI services. This requires `buildx`, which is not installed by default. If you haven’t used `buildx` before, you can install it by running: `docker buildx install` **Note:** The dot argument `.` indicates that your build context (place of the **Dockerfile** and other needed files) is the current directory. **Note:** The `-t` argument allows you to choose the identifier to give to your image. Usually, image identifiers are composed of a **name** and a **version tag** `:`. For this example, we chose **streamlit-eda-iris:latest**.   ### Test it locally (optional) Launch the following **Docker command** to launch your application locally on your computer: ```console docker run --rm -it -p 8501:8501 --user=42420:42420 streamlit-eda-iris:latest ``` **Note:** The `-p 8501:8501` argument indicates that you want to execute a port redirection from the port **8501** of your local machine into the port **8501** of the Docker container. The port **8501** is the default port used by **Streamlit** applications. **Warning:** **NOTE:** Don't forget the `--user=42420:42420` argument if you want to simulate the exact same behavior that will occur on **AI Deploy apps**. It executes the Docker container as the specific OVHcloud user (user **42420:42420**). Once started, your application should be available on `http://localhost:8501`.   ### Push the image into the shared registry **Warning:** **NOTE:** The shared registry should only be used for testing purposes. Please consider creating and attaching your own registry. More information about this can be found [here](https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/manage-registries.md). The images pushed to this registry are for AI Tools workloads only, and will not be accessible for external uses. Find the address of your shared registry by launching this command: ```console ovhai registry list ``` Log in on the shared registry with your usual AI Platform user credentials: ```console docker login -u -p ``` Push the compiled image into the shared registry: ```console docker tag streamlit-eda-iris:latest /streamlit-eda-iris:latest docker push /streamlit-eda-iris:latest ```   ### Launch the AI Deploy app The following command starts a new app running your Streamlit application: ```console ovhai app run \ --default-http-port 8501 \ --cpu 12 \ /streamlit-eda-iris:latest ``` **Note:** `--default-http-port 8501` indicates that the port to reach on the app URL is the `8501`. `--cpu 12` indicates that we request 12 CPUs for that app. **Note:** Consider adding the `--unsecure-http` attribute if you want your application to be reachable without any authentication.   ## Go further - You can imagine deploying an AI model with an other tool: **Gradio**. Refer to this [tutorial](https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/ai-deploy-gradio-sketch-recognition.md). Browse all the [AI & Machine Learning guides](https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/landing-page-ai-machine-learning.md). Browse the rest of the [OVHcloud US documentation](https://docs.us.ovhcloud.com/en/index.md) for guides on our other products and services. Learn more about [AI & Machine Learning](https://us.ovhcloud.com/public-cloud/ai-machine-learning/) on the OVHcloud US website. If you need training or technical assistance to implement our solutions, contact your sales representative or click on [this link](https://us.ovhcloud.com/professional-services/) to get a quote and ask our Professional Services experts for a custom analysis of your project.