Create app.py

app.py

@@ -0,0 +1,284 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+import requests
+import io
+from transformers import pipeline
+
+#import streamlit as st
+#import pandas as pd
+#import matplotlib.pyplot as plt
+
+
+
+st.title('Playing cards Image Analysis')
+
+
+#sample slider; feel free to remove:
+#x = st.slider('Select a value')
+#st.write(x, 'squared is', x * x)
+
+'''
+This next piece of code will hit GitHub for two csv files
+One is the original dataset, broken up into test, train, valid.
+The second csv is the test dataset, with the results after the models were run through the API
+'''
+# Downloading the csv file from your GitHub account
+url = "https://huggingface.co/datasets/rwcuffney/autotrain-data-pick_a_card/raw/main/cards.csv" 
+download = requests.get(url).content
+
+# Reading the downloaded content and turning it into a pandas data frame
+df = pd.read_csv(io.StringIO(download.decode('utf-8')))
+#df = pd.read_csv('playing_cards/cards.csv').sort_values('class index')
+df_fulldataset=df
+
+# Downloading the csv file from your GitHub account
+url = "https://huggingface.co/datasets/rwcuffney/autotrain-data-pick_a_card/raw/main/ML_results.csv" 
+download = requests.get(url).content
+
+# Reading the downloaded content and turning it into a pandas data frame
+df = pd.read_csv(io.StringIO(download.decode('utf-8')))
+#df = pd.read_csv('playing_cards/cards.csv').sort_values('class index')
+df_test = df
+
+
+
+# Create the button
+if st.button('Click me to re-run code',key='RunCode_button'):
+    # Call the function when the button is clicked
+    st.experimental_rerun()
+
+st.header('Sample of the .csv data:')
+x = st.slider('Select a value',value=10,max_value=8000)
+st.table(df_fulldataset.sample(x))
+
+### HORIZONTAL BAR ###
+
+st.header('Distribution of the playing card images:')
+
+# Get the value counts of the 'labels' column
+value_counts = df_fulldataset.groupby('labels')['class index'].count().iloc[::-1]
+
+
+fig, ax = plt.subplots(figsize=(10,10))
+    
+# Create a bar chart of the value counts
+ax = value_counts.plot.barh()
+# Set the chart title and axis labels
+ax.set_title('Value Counts of Labels')
+ax.set_xlabel('Label')
+ax.set_ylabel('Count')
+
+# Show the chart
+st.pyplot(fig)
+
+
+### PIE CHART ###
+
+st.header('Balance of Train,Valid,Test datasets:')
+
+# Get the value counts of the 'labels' column
+value_counts = df_fulldataset.groupby('data set')['class index'].count().iloc[::-1]
+
+value_counts =df_fulldataset['data set'].value_counts()
+
+fig, ax = plt.subplots(figsize=(5,5)
+                      )
+# Create a bar chart of the value counts
+ax = value_counts.plot.pie(autopct='%1.1f%%')
+
+# Set the chart title and axis labels
+# Show the chart
+st.pyplot(fig)
+
+
+
+
+
+models_run= ['SwinForImageClassification_24', 
+             'ViTForImageClassification_22',
+             'SwinForImageClassification_21', 
+             'ResNetForImageClassification_23',
+             'BeitForImageClassification_25']
+
+
+from enum import Enum
+ 
+API_dict = dict(
+    SwinForImageClassification_21="https://api-inference.huggingface.co/models/rwcuffney/autotrain-pick_a_card-3726099221",
+    ViTForImageClassification_22="https://api-inference.huggingface.co/models/rwcuffney/autotrain-pick_a_card-3726099222",
+    ResNetForImageClassification_23= "https://api-inference.huggingface.co/models/rwcuffney/autotrain-pick_a_card-3726099223",
+    SwinForImageClassification_24 = "https://api-inference.huggingface.co/models/rwcuffney/autotrain-pick_a_card-3726099224",
+    BeitForImageClassification_25="https://api-inference.huggingface.co/models/rwcuffney/autotrain-pick_a_card-3726099225")
+
+
+# printing enum member as string
+#print(Api_URL.ViTForImageClassification_22.value)
+
+
+####Try it out ###
+import requests
+
+st.header("Try it out")
+
+'''
+Warning: it will error out at first, resubmit a few times.
+Each model needs to 'warm up' before they start working.
+
+You can use any image... try test/queen of hearts/4.jpg to see an example that 
+Got different results with different models
+'''
+
+headers = {"Authorization": "Bearer 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"}
+def query(filename,api_url):
+    #with open(filename, "rb") as f:
+        #data = f.read()
+    response = requests.post(api_url, headers=headers, data=filename)
+    return response.json()
+
+#API_URL = "https://api-inference.huggingface.co/models/rwcuffney/autotrain-pick_a_card-3726099224"
+
+
+pipeline = pipeline(task="image-classification", model="rwcuffney/autotrain-pick_a_card-3726099224")
+def predict(image):
+    predictions = pipeline(image)
+    return {p["label"]: p["score"] for p in predictions}
+
+
+##### FORM #####
+
+with st.form("api_form"):
+    api = st.selectbox('Which model do you want to try?',models_run,key='select_box')
+
+
+
+
+    uploaded_file = st.file_uploader("Choose a file")
+    if uploaded_file is not None:
+        # To read file as bytes:
+        #bytes_data = uploaded_file.getvalue()
+        #st.write(bytes_data)
+        st.image(uploaded_file)
+
+
+    submitted = st.form_submit_button("Submit")
+    if submitted:
+        #st.write(API_dict[api])
+        #output = query(bytes_data,API_dict[api])
+
+        #prediction = output[0]['label']
+        #st.write(f'prediction = {prediction}')
+        #st.text(output)
+        prediction = predict(uploaded_file)
+        st.write(prediction)
+
+
+
+
+#### FUNCTIONS ####
+import sklearn
+from sklearn import metrics
+import matplotlib.pyplot as plt
+
+index = ['accuracy_score','Weighted f1', 'Cohen Kappa','Matthews']
+df_Metrics =pd.DataFrame(index=index)
+
+labels = df_test['labels'].unique()
+
+
+
+### FUNCTION TO SHOW THE METRICS
+def show_metrics(test,pred,name):
+    from sklearn import metrics
+    
+    my_Name = name
+    my_Accuracy_score=metrics.accuracy_score(test, pred)
+    #my_ROC_AUC_score= roc_auc_score(y, model.predict_proba(X), multi_class='ovr')
+    my_Weighted_f1= metrics.f1_score(test, pred,average='weighted')
+    my_Cohen_Kappa = metrics.cohen_kappa_score(test, pred)
+    my_Matthews_coefficient=metrics.matthews_corrcoef(test, pred)
+    
+    st.header(f'Metrics for {my_Name}:')	
+    report =metrics.classification_report(test, pred, output_dict=True)
+    df_report = pd.DataFrame(report).transpose()	
+    st.dataframe(df_report )
+    st.write(f'Accuracy Score........{metrics.accuracy_score(test, pred):.4f}\n\n' \
+          #f'ROC AUC Score.........{my_ROC_AUC_score:.4f}\n\n' \
+          f'Weighted f1 score.....{my_Weighted_f1:.4f}\n\n' \
+          f'Cohen Kappa...........{my_Cohen_Kappa:.4f}\n\n' \
+          f'Matthews Coefficient..{my_Matthews_coefficient:.4f}\n\n')
+    my_List = [my_Accuracy_score, my_Weighted_f1, my_Cohen_Kappa, my_Matthews_coefficient]
+
+    df_Metrics[my_Name] = my_List
+    
+    cfm= metrics.confusion_matrix(test, pred)
+    st.caption(f'Confusion Matrix: {my_Name}')
+    cmd = metrics.ConfusionMatrixDisplay(cfm,display_labels=labels)
+    fig, ax = plt.subplots(figsize=(15,15))
+    ax = cmd.plot(ax=ax, 
+                  colorbar=False,
+                  values_format = '.0f',
+                  cmap='Reds')#='tab20')# see color options here https://matplotlib.org/stable/tutorials/colors/colormaps.html
+    plt.xticks(rotation=90)
+    st.pyplot(fig)
+
+
+
+
+
+st.header('Let\'s see how the models performed')
+
+'''
+The next part of the code will analyze the full dataset.
+Choose all five models to compare them all
+
+'''
+
+
+##### FORM #####
+
+with st.form("my_form"):
+    st.write("You can choose from 1 to 5 models")
+
+
+    selected_options = st.multiselect(
+    'Which models would you like to analyze?', models_run)
+
+    submitted = st.form_submit_button("Submit")
+    if submitted:
+        st.write('you selected',selected_options)
+
+
+    ###Show the metrics for each dataset:
+        test = df_test['labels']
+
+        #for m in models_run:
+        for m in selected_options:
+            pred = df_test[m]
+            show_metrics(test,pred,m)
+
+        st.header('Metrics for all models:')
+        st.table(df_Metrics)
+
+        #### GRAPH THE RESULTS ###
+        import seaborn as sns
+
+        # Reshape the dataframe into long format using pd.melt()
+        #subset_df = pd.melt(df_Metrics[['SwinForImageClassification_24', 
+        #'ViTForImageClassification_22', 'SwinForImageClassification_21', 'ResNetForImageClassification_23', 'BeitForImageClassification_25']].reset_index(), id_vars='index', var_name='Model', value_name='Score')
+        subset_df = pd.melt(df_Metrics[selected_options].reset_index(), id_vars='index', var_name='Model', value_name='Score')
+
+        sns.set_style('whitegrid')
+        ax=sns.catplot(data=subset_df, 
+                    x='index', 
+                    y='Score', 
+                    hue='Model', 
+                    kind='bar', 
+                    palette='Blues', 
+                    aspect=2)
+
+        plt.xlabel('Clusters')
+        plt.ylabel('Scores')
+
+        fig = ax.figure
+        st.pyplot(fig)