Py.Cafe
🌸 Interactive Iris Dataset Exploration
- app.py
- requirements.txt
app.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
# app.py
import streamlit as st
import pandas as pd
import plotly.express as px
from sklearn.datasets import load_iris
# Page configuration
st.set_page_config(
page_title="Iris Interactive Dashboard",
layout="wide"
)
st.title("🌸 Interactive Iris Dataset Dashboard")
st.write(
"This dashboard allows users to explore the Iris dataset "
"using interactive filters and dynamic visualizations."
)
# Load and prepare data
@st.cache_data
def load_data():
iris = load_iris(as_frame=True)
df = iris.frame
df["species"] = df["target"].map(
dict(enumerate(iris.target_names))
)
return df, iris.feature_names
df, feature_names = load_data()
# Sidebar controls
st.sidebar.header("Filter Options")
species_selected = st.sidebar.multiselect(
"Select species:",
options=df["species"].unique(),
default=df["species"].unique()
)
x_axis = st.sidebar.selectbox(
"Select X-axis:",
options=feature_names,
index=0
)
y_axis = st.sidebar.selectbox(
"Select Y-axis:",
options=feature_names,
index=1
)
# Filter data
filtered_df = df[df["species"].isin(species_selected)]
# Key metrics
st.subheader("Key Statistics")
col1, col2, col3 = st.columns(3)
col1.metric("Total Observations", len(filtered_df))
col2.metric("Species Count", filtered_df["species"].nunique())
col3.metric(
"Average Sepal Length (cm)",
round(filtered_df["sepal length (cm)"].mean(), 2)
)
# Scatter plot
st.subheader("Feature Relationship")
scatter_fig = px.scatter(
filtered_df,
x=x_axis,
y=y_axis,
color="species",
title=f"{y_axis} vs {x_axis}",
hover_data=feature_names
)
st.plotly_chart(scatter_fig, use_container_width=True)
# Distribution plot
st.subheader("Feature Distribution")
feature_selected = st.selectbox(
"Select feature to view distribution:",
feature_names
)
hist_fig = px.histogram(
filtered_df,
x=feature_selected,
color="species",
barmode="overlay",
opacity=0.7,
title=f"Distribution of {feature_selected}"
)
st.plotly_chart(hist_fig, use_container_width=True)
# Data preview
with st.expander("View Filtered Data"):
st.dataframe(filtered_df)
app.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
# app.py
import streamlit as st
import pandas as pd
import plotly.express as px
from sklearn.datasets import load_iris
# Page configuration
st.set_page_config(
page_title="Iris Interactive Dashboard",
layout="wide"
)
st.title("🌸 Interactive Iris Dataset Dashboard")
st.write(
"This dashboard allows users to explore the Iris dataset "
"using interactive filters and dynamic visualizations."
)
# Load and prepare data
@st.cache_data
def load_data():
iris = load_iris(as_frame=True)
df = iris.frame
df["species"] = df["target"].map(
dict(enumerate(iris.target_names))
)
return df, iris.feature_names
df, feature_names = load_data()
# Sidebar controls
st.sidebar.header("Filter Options")
species_selected = st.sidebar.multiselect(
"Select species:",
options=df["species"].unique(),
default=df["species"].unique()
)
x_axis = st.sidebar.selectbox(
"Select X-axis:",
options=feature_names,
index=0
)
y_axis = st.sidebar.selectbox(
"Select Y-axis:",
options=feature_names,
index=1
)
# Filter data
filtered_df = df[df["species"].isin(species_selected)]
# Key metrics
st.subheader("Key Statistics")
col1, col2, col3 = st.columns(3)
col1.metric("Total Observations", len(filtered_df))
col2.metric("Species Count", filtered_df["species"].nunique())
col3.metric(
"Average Sepal Length (cm)",
round(filtered_df["sepal length (cm)"].mean(), 2)
)
# Scatter plot
st.subheader("Feature Relationship")
scatter_fig = px.scatter(
filtered_df,
x=x_axis,
y=y_axis,
color="species",
title=f"{y_axis} vs {x_axis}",
hover_data=feature_names
)
st.plotly_chart(scatter_fig, use_container_width=True)
# Distribution plot
st.subheader("Feature Distribution")
feature_selected = st.selectbox(
"Select feature to view distribution:",
feature_names
)
hist_fig = px.histogram(
filtered_df,
x=feature_selected,
color="species",
barmode="overlay",
opacity=0.7,
title=f"Distribution of {feature_selected}"
)
st.plotly_chart(hist_fig, use_container_width=True)
# Data preview
with st.expander("View Filtered Data"):
st.dataframe(filtered_df)