Update app.py

app.py

@@ -21,53 +21,65 @@ def load_file(uploaded_file):
         st.error(f"Error loading file: {e}")
         return None
 
+# Function to infer column names based on synonyms
+def infer_column(data, synonyms):
+    """Infer a column name based on synonyms."""
+    for column in data.columns:
+        if column.lower() in synonyms:
+            return column
+    return None
+
 # Function to generate graph based on user query
 def generate_graph(data, query):
     """Generate a graph based on user query."""
     try:
         fig, ax = plt.subplots(figsize=(10, 6))
 
-        if "bar" in query.lower() and "gross sales" in query.lower():
+        # Infer column names
+        country_col = infer_column(data, {"country", "countries"})
+        sales_col = infer_column(data, {"gross_sales", "sales", "revenue"})
+        date_col = infer_column(data, {"date", "time"})
+
+        if "bar" in query.lower() and country_col and sales_col:
             # Bar chart for countries and gross sales
-            if 'country' in data.columns and 'gross_sales' in data.columns:
-                country_data = data[['country', 'gross_sales']].groupby('country').sum().reset_index()
-                sns.barplot(x='country', y='gross_sales', data=country_data, ax=ax, color='skyblue')
-                ax.set_xticklabels(ax.get_xticklabels(), rotation=45, ha='right')
-                st.pyplot(fig)
-            else:
-                st.error("The dataset must contain 'country' and 'gross_sales' columns.")
-        elif "line" in query.lower() and "sales trend" in query.lower():
+            country_data = data[[country_col, sales_col]].groupby(country_col).sum().reset_index()
+            sns.barplot(x=country_col, y=sales_col, data=country_data, ax=ax, color='skyblue')
+            ax.set_xticklabels(ax.get_xticklabels(), rotation=45, ha='right')
+            ax.set_title(f"Bar Chart: {country_col} vs {sales_col}")
+            st.pyplot(fig)
+        elif "line" in query.lower() and date_col and sales_col:
             # Line chart for sales trend over time
-            if 'date' in data.columns and 'sales' in data.columns:
-                data['date'] = pd.to_datetime(data['date'])
-                sales_trend = data.groupby('date')['sales'].sum().reset_index()
-                sns.lineplot(x='date', y='sales', data=sales_trend, ax=ax)
-                ax.set_title("Sales Trend Over Time")
-                st.pyplot(fig)
-            else:
-                st.error("The dataset must contain 'date' and 'sales' columns.")
-        elif "scatter" in query.lower() and "relationship" in query.lower():
+            data[date_col] = pd.to_datetime(data[date_col])
+            sales_trend = data.groupby(date_col)[sales_col].sum().reset_index()
+            sns.lineplot(x=date_col, y=sales_col, data=sales_trend, ax=ax)
+            ax.set_title(f"Line Chart: {sales_col} Over Time")
+            st.pyplot(fig)
+        elif "scatter" in query.lower():
             # Scatter plot for relationships
-            columns = query.lower().split("between")[-1].strip().split("and")
-            x_col = columns[0].strip()
-            y_col = columns[1].strip()
-
-            if x_col in data.columns and y_col in data.columns:
-                sns.scatterplot(x=x_col, y=y_col, data=data, ax=ax)
-                ax.set_title(f"Scatter Plot: {x_col} vs {y_col}")
-                st.pyplot(fig)
-            else:
-                st.error(f"The dataset must contain '{x_col}' and '{y_col}' columns.")
+            if "between" in query.lower():
+                columns = query.lower().split("between")[-1].strip().split("and")
+                if len(columns) == 2:
+                    x_col = infer_column(data, {columns[0].strip()})
+                    y_col = infer_column(data, {columns[1].strip()})
+
+                    if x_col and y_col:
+                        sns.scatterplot(x=x_col, y=y_col, data=data, ax=ax)
+                        ax.set_title(f"Scatter Plot: {x_col} vs {y_col}")
+                        st.pyplot(fig)
+                        return
+            st.error("Please specify valid columns for the scatter plot.")
         elif "histogram" in query.lower():
             # Histogram for a specified column
-            column = query.lower().split("for")[-1].strip()
-
-            if column in data.columns:
-                sns.histplot(data[column], bins=20, kde=True, ax=ax, color='green')
-                ax.set_title(f"Histogram of {column}")
-                st.pyplot(fig)
-            else:
-                st.error(f"The dataset must contain the column '{column}'.")
+            if "for" in query.lower():
+                column = query.lower().split("for")[-1].strip()
+                hist_col = infer_column(data, {column})
+
+                if hist_col:
+                    sns.histplot(data[hist_col], bins=20, kde=True, ax=ax, color='green')
+                    ax.set_title(f"Histogram of {hist_col}")
+                    st.pyplot(fig)
+                    return
+            st.error("Please specify a valid column for the histogram.")
         else:
             st.error("Unsupported graph type. Try asking for a bar chart, line chart, scatter plot, or histogram.")
     except Exception as e: