app.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt

MYDIR = '/Users/rwcuffney/Documents/NorthWestern_University/Machine_Learning/Module7_Assingment/'

x = st.slider('Select a value')
st.write(x, 'squared is', x * x)


df = pd.read_csv(MYDIR +'playing_cards/cards.csv').sort_values('class index')
df_test = df[df['data set']=='test']
df_train = df[df['data set']=='train']
df_validate = df[df['data set']=='validate']



### HORIZONTAL BAR ###


# Get the value counts of the 'labels' column
value_counts = df.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 ###

# Get the value counts of the 'labels' column
value_counts = df.groupby('data set')['class index'].count().iloc[::-1]

value_counts =df['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
ax.set_title('Train, Validate, Test Distribution')
# Show the chart
st.pyplot(fig)