Task-272 Research on the basics for using Streamlit

Pipfile

@@ -5,6 +5,8 @@ name = "pypi"
 
 [packages]
 streamlit = "*"
+pandas = "*"
+numpy = "*"
 
 [dev-packages]
 

Pipfile.lock

@@ -1,7 +1,7 @@
 {
     "_meta": {
         "hash": {
-            "sha256": "2fb0e7ed9ca1b350b37caefdfe413c4076829b44027d92b7e29e8cfe03b41220"
+            "sha256": "c16e5f3fc76a1450c8e733093365a95a5f7d169ef54be7e83124c7fa917855da"
         },
         "pipfile-spec": 6,
         "requires": {
@@ -367,6 +367,7 @@
                 "sha256:f4ca91d61a4bf61b0f2228f24bbfa6a9facd5f8af03759fe2a655c50ae2c6610",
                 "sha256:f6b3dfc7661f8842babd8ea07e9897fe3d9b69a1d7e5fbb743e4160f9387833b"
             ],
+            "index": "pypi",
             "markers": "python_version >= '3.10'",
             "version": "==2.2.3"
         },
@@ -423,6 +424,7 @@
                 "sha256:f3a255b2c19987fbbe62a9dfd6cff7ff2aa9ccab3fc75218fd4b7530f01efa24",
                 "sha256:fffb8ae78d8af97f849404f21411c95062db1496aeb3e56f146f0355c9989319"
             ],
+            "index": "pypi",
             "markers": "python_version >= '3.9'",
             "version": "==2.2.3"
         },

research/Steamlit_Research.md

@@ -0,0 +1,63 @@
+# Streamlit Research:
+### Creating the application:
+ - Import Streamlit library
+
+```
+import streamlit as st
+```
+
+ - Running the Streamlit app:
+    - This will open a separate browser window running the application locally
+```
+streamlit run <app_name>.py
+```
+
+
+### State driven UI:
+ - Elements can be loaded into variables and those variables can be used to modify the specified element:
+    ```
+    text_element_state = st.text('Element State Test')  ## Initializes the element with this text
+    text_element_state.text('New Element State Test')   ## Updates the displayed text
+    ```
+
+ - Can also using caching:
+    - Minimizes overhead of running functions everytime the application reloads by checking the passed values to see if they have changed and only running the method if they have
+        ```
+        @st.cache_data
+        def load_data(args):
+            ## Some logic
+
+        text_element_state.text('Some data: (using st.cache_data)') ## This will appear immediately upon saving
+        ```
+ - There are some limitations with using the cache mechanism:
+    - Will not work with functions with internal numerical randomization (with regards to calculations)
+    - Scope of the validation is within the current working directory
+    - Cached values are stored by reference, so it is undesirable to mutate the values
+ - st.write() function:
+    - Can pass more complex data types that will be displayed in an interactable format
+        - i.e., dataframes can be passed and displayed automatically as a table
+ - Additional functionality that is available:
+    - Draw histograms by using numpy:
+        ```
+        st.subheader('Number of pickups by hour')
+        hist_values = np.histogram(
+            data[DATE_COLUMN].dt.hour, bins=24, range=(0,24))[0]
+        st.bar_chart(hist_values)
+        ```
+    - Plot data on map:
+        ```
+        hour_to_filter = 17
+        filtered_data = data[data[DATE_COLUMN].dt.hour == hour_to_filter]
+        st.subheader(f'Map of all pickups at {hour_to_filter}:00')
+        st.map(filtered_data)
+        ```
+    - Filter data using slider:
+        ```
+        hour_to_filter = st.slider('hour', 0, 23, 17)  # min: 0h, max: 23h, default: 17h
+        ```
+    - Using buttons for toggling data:
+        ```
+        if st.checkbox('Show raw data'):
+            st.subheader('Raw data')
+            st.write(data)
+        ```

research/basic_streamlit_concepts.py

@@ -0,0 +1,35 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+
+st.write("Basic Dataframe Display")
+dataframe = pd.DataFrame({
+    'first column': [1, 2, 3, 4],
+    'second column': [10, 20, 30, 40]
+})
+st.write(dataframe)
+
+st.write("Numpy (Randomized) Dataframe Display")
+dataframe = np.random.randn(10, 20)
+st.dataframe(dataframe)
+
+st.write("Use of Styling to highlight specific cells")
+dataframe = pd.DataFrame(
+    np.random.randn(10, 20),
+    columns=('col %d' % i for i in range(20)))
+
+st.dataframe(dataframe.style.highlight_max(axis=0))
+
+st.write('Displaying Charts')
+chart_data = pd.DataFrame(
+     np.random.randn(20, 3),
+     columns=['a', 'b', 'c'])
+
+st.line_chart(chart_data)
+
+st.write('Displaying Maps')
+map_data = pd.DataFrame(
+    np.random.randn(1000, 2) / [50, 50] + [37.76, -122.4],
+    columns=['lat', 'lon'])
+
+st.map(map_data)

research/streamlit_widgets.py

@@ -0,0 +1,31 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+
+st.write('Sliders:')
+slider_val = st.slider('Data Slider') 
+st.write(slider_val, 'squared is', slider_val * slider_val)
+
+st.write('Reference by Widget Name:')
+st.text_input("Text Entry", key="text")
+st.session_state.text
+
+st.write('Checkboxes:')
+if st.checkbox('Show dataframe'):
+    chart_data = pd.DataFrame(
+       np.random.randn(20, 3),
+       columns=['a', 'b', 'c'])
+
+    chart_data
+
+st.write('Selectboxes:')
+df = pd.DataFrame({
+    'first column': [1, 2, 3, 4],
+    'second column': [10, 20, 30, 40]
+    })
+
+option = st.selectbox(
+    'Favorite Number?',
+     df['first column'])
+
+'Selected Number: ', option