fix: update Python version to 3.12 and remove unnecessary packages from Dockerfile

src/app.py → app.py

@@ -1,15 +1,11 @@
 import streamlit as st
 import pandas as pd
-import plotly.express as px 
+import plotly.express as px
 import plotly.graph_objects as go
 import numpy as np
 
 ### CONFIG
-st.set_page_config(
-    page_title="E-commerce",
-    page_icon="💸",
-    layout="wide"
-  )
+st.set_page_config(page_title="E-commerce", page_icon="💸", layout="wide")
 
 ### TITLE AND TEXT
 st.title("Build dashboards with Streamlit 🎨")
@@ -22,30 +18,34 @@ st.markdown("""
 """)
 
 ### LOAD DATA
-DATA_PRICING = ('../Data/get_around_pricing_project.csv')
+DATA_PRICING = "Data/get_around_pricing_project.csv"
 
-DATA_ANALYSIS = ('../Data/get_around_delay_analysis.csv')
+DATA_ANALYSIS = "Data/get_around_delay_analysis.csv"
 
-# this lets the cache activated : usage d'un décorateur python pour ajouter des fonctionnalité 
+
+# this lets the cache activated : usage d'un décorateur python pour ajouter des fonctionnalité
 # : st.cache_data et st.cache_resource qui remplace st.cache qui va devenir obsolète.
 # https://docs.streamlit.io/develop/api-reference/caching-and-state/st.cache_data
 # https://docs.streamlit.io/develop/api-reference/caching-and-state/st.cache_resource
-@st.cache_data 
+@st.cache_data
 def load_data(file, nrows, delimiter=","):
-    data = pd.read_csv(file, nrows=nrows,delimiter=delimiter)
-    #data["Date"] = data["Date"].apply(lambda x: pd.to_datetime(",".join(x.split(",")[-2:])))
-    #data["currency"] = data["currency"].apply(lambda x: pd.to_numeric(x[1:]))
+    data = pd.read_csv(file, nrows=nrows, delimiter=delimiter)
+    # data["Date"] = data["Date"].apply(lambda x: pd.to_datetime(",".join(x.split(",")[-2:])))
+    # data["currency"] = data["currency"].apply(lambda x: pd.to_numeric(x[1:]))
     return data
 
-data_load_state = st.text('Loading data...')
-data_pricing = load_data(DATA_PRICING,1000)
-data_analysis = load_data(DATA_ANALYSIS,1000)
-data_load_state.text("") # change text from "Loading data..." to "" once the the load_data function has run
+
+data_load_state = st.text("Loading data...")
+data_pricing = load_data(DATA_PRICING, 1000)
+data_analysis = load_data(DATA_ANALYSIS, 1000)
+data_load_state.text(
+    ""
+)  # change text from "Loading data..." to "" once the the load_data function has run
 
 ## Run the below code if the check is checked ✅
-if st.checkbox('Show raw data'):
-    st.subheader('Raw data')
-    st.write(data_pricing) 
+if st.checkbox("Show raw data"):
+    st.subheader("Raw data")
+    st.write(data_pricing)
 ### SHOW GRAPH STREAMLIT
 
 price_per_model = data_pricing["price"]
@@ -64,7 +64,9 @@ st.markdown("""
     * ...
     This way, you have all the flexibility you need to build awesome dashboards. 🥰
 """)
-fig = px.histogram(data.sort_values("country"), x="country", y="currency", barmode="group")
+fig = px.histogram(
+    data.sort_values("country"), x="country", y="currency", barmode="group"
+)
 st.plotly_chart(fig, use_container_width=True)
 
 
@@ -93,24 +95,36 @@ col1, col2 = st.columns(2)
 with col1:
     # visu des widgets
     st.markdown("First column")
-    car_id= st.selectbox("Select a country you want to see all time sales", data_analysis["car_id"].sort_values().unique())
+    car_id = st.selectbox(
+        "Select a country you want to see all time sales",
+        data_analysis["car_id"].sort_values().unique(),
+    )
     # intelligence et contrôle du widget
-    rental_canceled = data_analysis[data_analysis["state"]=="canceled"]
-    fig = px.histogram(rental_canceled, x="time_delta_with_previous_rental_in_minutes", y="delay_at_checkout_in_minutes")
+    rental_canceled = data_analysis[data_analysis["state"] == "canceled"]
+    fig = px.histogram(
+        rental_canceled,
+        x="time_delta_with_previous_rental_in_minutes",
+        y="delay_at_checkout_in_minutes",
+    )
     fig.update_layout(bargap=0.2)
     st.plotly_chart(fig, use_container_width=True)
 
 with col2:
     st.markdown("Second column")
     with st.form("average_sales_per_country"):
-      model = st.selectbox("Select a model you want to see", data_pricing["model_key"].sort_values().unique())
-      power = st.selectbox("Select a start date you want to see your metric",data_pricing["engine_power"].sort_values().unique())
-      submit = st.form_submit_button("submit")
-      if submit:
-              model_select = data_pricing[data_pricing["model_key"]==model]
-              power_select = data_pricing[data_pricing["power"]==power]
-              avg_rental_price = data_pricing[model_select & power_select ]["rental_price_per_day"].mean()
-              st.metric("Average rental price (in $)", np.round(avg_rental_price, 2))
-
-
-
+        model = st.selectbox(
+            "Select a model you want to see",
+            data_pricing["model_key"].sort_values().unique(),
+        )
+        power = st.selectbox(
+            "Select a start date you want to see your metric",
+            data_pricing["engine_power"].sort_values().unique(),
+        )
+        submit = st.form_submit_button("submit")
+        if submit:
+            model_select = data_pricing[data_pricing["model_key"] == model]
+            power_select = data_pricing[data_pricing["power"] == power]
+            avg_rental_price = data_pricing[model_select & power_select][
+                "rental_price_per_day"
+            ].mean()
+            st.metric("Average rental price (in $)", np.round(avg_rental_price, 2))

src/streamlit_app.py

@@ -1,40 +0,0 @@
-import altair as alt
-import numpy as np
-import pandas as pd
-import streamlit as st
-
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))