Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,196 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import numpy as np
+import plotly.express as px
+from scipy import stats
+import io
+
+# Metadata
+AUTHOR = "Eduardo Nacimiento García"
+EMAIL = "enacimie@ull.edu.es"
+LICENSE = "Apache 2.0"
+
+# Page config
+st.set_page_config(
+    page_title="SimpleStats",
+    page_icon="📊",
+    layout="wide",
+    initial_sidebar_state="expanded",
+)
+
+# Title and credits
+st.title("📊 SimpleStats")
+st.markdown(f"**Author:** {AUTHOR} | **Email:** {EMAIL} | **License:** {LICENSE}")
+
+st.write("""
+Upload a CSV file or try the built-in demo dataset to perform statistical analysis: summary, charts, hypothesis tests, and more.
+""")
+
+# Generate demo dataset
+@st.cache_data
+def create_demo_data():
+    np.random.seed(42)
+    n = 200
+    data = {
+        "Age": np.random.normal(35, 12, n).astype(int),
+        "Income": np.random.normal(45000, 15000, n),
+        "Satisfaction": np.random.randint(1, 11, n),  # scale 1-10
+        "Group": np.random.choice(["A", "B", "C"], n),
+        "Gender": np.random.choice(["M", "F"], n, p=[0.6, 0.4]),
+        "Purchase": np.random.choice([0, 1], n, p=[0.7, 0.3])
+    }
+    df = pd.DataFrame(data)
+    # Introduce some nulls for demo
+    df.loc[np.random.choice(df.index, 10), "Income"] = np.nan
+    df.loc[np.random.choice(df.index, 5), "Age"] = np.nan
+    return df
+
+demo_df = create_demo_data()
+
+# Button to load demo data
+if st.button("🧪 Load Demo Dataset"):
+    st.session_state['uploaded_file'] = demo_df.to_csv(index=False).encode('utf-8')
+    st.session_state['file_name'] = "demo_data.csv"
+    st.success("✅ Demo dataset loaded. Explore the features!")
+
+# File uploader
+uploaded_file = st.file_uploader("📂 Upload your CSV file", type=["csv"])
+
+# Determine data source
+if 'uploaded_file' in st.session_state and not uploaded_file:
+    # Use demo if no file uploaded
+    csv_bytes = st.session_state['uploaded_file']
+    file_name = st.session_state['file_name']
+    df = pd.read_csv(io.BytesIO(csv_bytes))
+    st.info(f"Using demo dataset: `{file_name}`")
+elif uploaded_file is not None:
+    df = pd.read_csv(uploaded_file)
+    st.success("✅ File uploaded successfully.")
+else:
+    df = None
+
+if df is not None:
+    # Show data preview
+    with st.expander("🔍 Data Preview (first 10 rows)"):
+        st.dataframe(df.head(10))
+
+    # Basic info
+    st.subheader("📌 Dataset Information")
+    col1, col2, col3 = st.columns(3)
+    col1.metric("Rows", df.shape[0])
+    col2.metric("Columns", df.shape[1])
+    col3.metric("Missing Values", df.isnull().sum().sum())
+
+    # Identify numeric and categorical columns
+    numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()
+    categorical_cols = df.select_dtypes(include=['object', 'category']).columns.tolist()
+
+    if len(numeric_cols) == 0:
+        st.warning("⚠️ No numeric columns found for statistical analysis.")
+    else:
+        st.subheader("📈 Descriptive Statistics")
+        st.dataframe(df[numeric_cols].describe())
+
+        # Histogram
+        st.subheader("📊 Histogram")
+        selected_col = st.selectbox("Select a numeric column for histogram:", numeric_cols)
+        fig_hist = px.histogram(df, x=selected_col, nbins=30, title=f"Histogram of {selected_col}", marginal="box")
+        st.plotly_chart(fig_hist, use_container_width=True)
+
+        # Scatter plot
+        if len(numeric_cols) >= 2:
+            st.subheader("📉 Scatter Plot")
+            col_x = st.selectbox("Select X-axis column:", numeric_cols, key="x")
+            col_y = st.selectbox("Select Y-axis column:", numeric_cols, key="y")
+            color_by = st.selectbox("Color by (optional):", [None] + categorical_cols, key="color")
+            if col_x != col_y:
+                fig_scatter = px.scatter(df, x=col_x, y=col_y, color=color_by, title=f"{col_x} vs {col_y}")
+                st.plotly_chart(fig_scatter, use_container_width=True)
+            else:
+                st.warning("⚠️ Please select two different columns.")
+
+        # Correlation matrix
+        st.subheader("🔗 Correlation Matrix")
+        corr = df[numeric_cols].corr()
+        fig_corr = px.imshow(corr, text_auto=".2f", aspect="auto", title="Correlation Matrix", color_continuous_scale='RdBu_r')
+        st.plotly_chart(fig_corr, use_container_width=True)
+
+        # Missing values per column
+        st.subheader("🕳️ Missing Values by Column")
+        nulls = df.isnull().sum()
+        if nulls.sum() > 0:
+            fig_nulls = px.bar(nulls, title="Missing Values by Column", labels={'value': 'Count', 'index': 'Column'}, color=nulls)
+            st.plotly_chart(fig_nulls, use_container_width=True)
+        else:
+            st.success("✅ No missing values in the dataset.")
+
+    # === STATISTICAL TESTS ===
+    st.header("🧪 Statistical Tests")
+
+    # Independent T-Test (for 2 groups)
+    if len(numeric_cols) > 0 and len(categorical_cols) > 0:
+        st.subheader("Independent T-Test (2 groups)")
+        t_num_col = st.selectbox("Numeric variable:", numeric_cols, key="t_num")
+        t_cat_col = st.selectbox("Categorical variable (must have exactly 2 groups):", 
+                                [col for col in categorical_cols if df[col].nunique() == 2], 
+                                key="t_cat")
+        if t_cat_col:
+            groups = df[t_cat_col].unique()
+            if len(groups) == 2:
+                group1 = df[df[t_cat_col] == groups[0]][t_num_col].dropna()
+                group2 = df[df[t_cat_col] == groups[1]][t_num_col].dropna()
+                t_stat, p_val = stats.ttest_ind(group1, group2, equal_var=False)
+                st.write(f"**T-Test result between `{groups[0]}` and `{groups[1]}` for `{t_num_col}`:**")
+                st.write(f"- **T-statistic:** {t_stat:.4f}")
+                st.write(f"- **P-value:** {p_val:.4f}")
+                if p_val < 0.05:
+                    st.success("🟢 Statistically significant difference (p < 0.05)")
+                else:
+                    st.error("🔴 No statistically significant difference (p >= 0.05)")
+            else:
+                st.warning("Selected categorical variable does not have exactly 2 groups.")
+
+    # ANOVA (for 3+ groups)
+    if len(numeric_cols) > 0 and len(categorical_cols) > 0:
+        st.subheader("ANOVA (3 or more groups)")
+        anova_num_col = st.selectbox("Numeric variable:", numeric_cols, key="anova_num")
+        anova_cat_col = st.selectbox("Categorical variable (3 or more groups):", 
+                                    [col for col in categorical_cols if df[col].nunique() >= 3], 
+                                    key="anova_cat")
+        if anova_cat_col:
+            groups = [df[df[anova_cat_col] == group][anova_num_col].dropna() for group in df[anova_cat_col].unique()]
+            if len(groups) >= 3:
+                f_stat, p_val = stats.f_oneway(*groups)
+                st.write(f"**ANOVA result for `{anova_num_col}` grouped by `{anova_cat_col}`:**")
+                st.write(f"- **F-statistic:** {f_stat:.4f}")
+                st.write(f"- **P-value:** {p_val:.4f}")
+                if p_val < 0.05:
+                    st.success("🟢 At least one group is significantly different (p < 0.05)")
+                else:
+                    st.error("🔴 No significant differences between groups (p >= 0.05)")
+
+    # Chi-Square Test (between two categorical variables)
+    if len(categorical_cols) >= 2:
+        st.subheader("Chi-Square Test (Association between categorical variables)")
+        chi_col1 = st.selectbox("First categorical variable:", categorical_cols, key="chi1")
+        chi_col2 = st.selectbox("Second categorical variable:", [col for col in categorical_cols if col != chi_col1], key="chi2")
+        if chi_col1 and chi_col2:
+            contingency_table = pd.crosstab(df[chi_col1], df[chi_col2])
+            chi2, p_val, dof, expected = stats.chi2_contingency(contingency_table)
+            st.write(f"**Chi-Square result between `{chi_col1}` and `{chi_col2}`:**")
+            st.write(f"- **Chi² statistic:** {chi2:.4f}")
+            st.write(f"- **P-value:** {p_val:.4f}")
+            st.write(f"- **Degrees of freedom:** {dof}")
+            if p_val < 0.05:
+                st.success("🟢 Variables are associated (p < 0.05)")
+            else:
+                st.error("🔴 No evidence of association between variables (p >= 0.05)")
+            with st.expander("📋 Contingency Table"):
+                st.dataframe(contingency_table)
+
+else:
+    st.info("👆 Upload a CSV file or click 'Load Demo Dataset' to get started.")
 
-"""
-# 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])),
-    ))
+# Footer
+st.markdown("---")
+st.caption(f"© {AUTHOR} | License {LICENSE} | Contact: {EMAIL}")