Upload 3 files

app.py

@@ -0,0 +1,81 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.linear_model import LinearRegression
+import re
+
+# Load the CSV file
+data = pd.read_csv('amazon.csv', delimiter=',')
+
+# Function to extract numeric values from a string (remove non-numeric characters)
+def extract_numeric_value(value):
+    numeric_value = re.sub(r'[^\d.]', '', value)
+    return float(numeric_value) if numeric_value else None
+
+# Convert 'actual_price' and 'rating' columns to numeric by removing non-numeric characters
+data['actual_price'] = data['actual_price'].apply(extract_numeric_value)
+data['rating'] = data['rating'].apply(extract_numeric_value)
+
+# Title
+st.title('Sales Forecasting and Product Analysis')
+
+# Sidebar filters
+category_filter = st.sidebar.selectbox('Select Category', data['category'].unique())
+product_filter = st.sidebar.selectbox('Select Product', data[data['category'] == category_filter]['product_name'].unique())
+
+filtered_data = data[(data['category'] == category_filter) & (data['product_name'] == product_filter)]
+
+# Display basic product information
+st.subheader('Product Information')
+st.write('Product ID:', filtered_data['product_id'].values[0])
+st.write('Product Name:', product_filter)
+st.write('Category:', category_filter)
+st.write('Discounted Price:', filtered_data['discounted_price'].values[0])
+st.write('Actual Price:', filtered_data['actual_price'].values[0])
+st.write('Discount Percentage:', filtered_data['discount_percentage'].values[0])
+st.write('Average Rating:', filtered_data['rating'].mean())
+st.write('Rating Count:', filtered_data['rating_count'].values[0])
+st.write('About Product:', filtered_data['about_product'].values[0])
+
+
+# Display product image
+product_image_url = filtered_data['img_link'].values[0]
+st.image(product_image_url, caption='Product Image', use_column_width=True)
+
+
+# Cumulative sales plot over rows (assumes rows are ordered chronologically)
+cumulative_sales_over_rows = filtered_data.index + 1
+st.subheader('Cumulative Sales Over Rows')
+fig, ax = plt.subplots(figsize=(10, 6))
+ax.plot(cumulative_sales_over_rows, filtered_data['actual_price'].cumsum())
+ax.set_xlabel('Rows')
+ax.set_ylabel('Cumulative Sales')
+st.pyplot(fig)
+
+# Sales forecasting using Linear Regression
+st.subheader('Sales Forecasting')
+forecast_days = st.number_input('Enter the number of days for sales forecasting:', min_value=1, value=7)
+
+# Convert the row index to numeric values
+row_numeric = cumulative_sales_over_rows.values.reshape(-1, 1)
+X = row_numeric
+y = filtered_data['actual_price'].cumsum().values
+model = LinearRegression()
+model.fit(X, y)
+
+# Generate future row indices for forecasting
+last_row = cumulative_sales_over_rows.max()
+forecast_rows = [last_row + i for i in range(1, forecast_days + 1)]
+forecast_rows_numeric = pd.Series(forecast_rows).values.reshape(-1, 1)
+
+# Predict cumulative sales for forecasted rows
+forecast_values = model.predict(forecast_rows_numeric)
+forecast_cumulative_sales = forecast_values
+
+forecast_df = pd.DataFrame({'Row': forecast_rows, 'Forecasted Cumulative Sales': forecast_cumulative_sales})
+st.write(forecast_df)
+
+
+# Footer
+st.text('Data Used: Amazon Sales Data')

reuirements.txt

@@ -0,0 +1,5 @@
+streamlit==0.87.0
+pandas==1.3.3
+matplotlib==3.4.3
+seaborn==0.11.2
+scikit-learn==0.24.2