add product and industry search functions

app.py

@@ -16,13 +16,26 @@ def load_pandas_xlsx(path):
 	data = pd.read_excel(path)
 	return data
 
-# @st.cache_data
 @st.cache_data
 def build_company_df(input_df):
 	# build company df
 	output_df = input_df[['companyLabel', 'companyLabelJA', 'company']].drop_duplicates()
 	return output_df
 
+@st.cache_data
+def build_industry_df(input_df):
+	# Pre compute unique number of companies per industry
+	output_df = input_df[['company', 'companyLabel', 'companyLabelJA', 'industry', 'industryLabel', 'industryLabelJA']].drop_duplicates().groupby(['industry', 'industryLabel', 'industryLabelJA'])['company'].count().sort_values(ascending=False).reset_index().copy()
+	output_df = output_df.rename(columns={'company': 'n_competitors'})
+	return output_df
+
+@st.cache_data
+def build_product_df(input_df):
+	# Pre compute unique number of companies per product
+	output_df = input_df[['company', 'companyLabel', 'companyLabelJA', 'product', 'productLabel', 'productLabelJA']].drop_duplicates().groupby(['product', 'productLabel', 'productLabelJA'])['company'].count().sort_values(ascending=False).reset_index().copy()
+	output_df = output_df.rename(columns={'company': 'n_competitors'})
+	return output_df
+
 def search_df(inp, df, col):
 	mask = df[col].str.contains(inp, case=False, regex=False)
 	select_df = df[mask]
@@ -48,8 +61,16 @@ st.success("Company Data Loaded!")
 ### Pre computation Steps ### 
 
 # Pre compute unique number of companies per industry
-industry_to_counts = competitor_df[['company', 'companyLabel', 'companyLabelJA', 'industry', 'industryLabel', 'industryLabelJA']].drop_duplicates().groupby(['industry', 'industryLabel', 'industryLabelJA'])['company'].count().sort_values(ascending=False).reset_index().copy()
-industry_to_counts = industry_to_counts.rename(columns={'company': 'n_competitors'})
+# industry_to_counts = competitor_df[['company', 'companyLabel', 'companyLabelJA', 'industry', 'industryLabel', 'industryLabelJA']].drop_duplicates().groupby(['industry', 'industryLabel', 'industryLabelJA'])['company'].count().sort_values(ascending=False).reset_index().copy()
+# industry_to_counts = industry_to_counts.rename(columns={'company': 'n_competitors'})
+
+industry_to_counts = build_industry_df(competitor_df)
+
+# Pre compute unique number of companies per industry
+# product_to_counts = competitor_df[['company', 'companyLabel', 'companyLabelJA', 'product', 'productLabel', 'productLabelJA']].drop_duplicates().groupby(['product', 'productLabel', 'productLabelJA'])['company'].count().sort_values(ascending=False).reset_index().copy()
+# product_to_counts = product_to_counts.rename(columns={'company': 'n_competitors'})
+
+product_to_counts = build_product_df(competitor_df)
 
 ### end ###
 
@@ -146,7 +167,7 @@ if option == "By Company":
 
 			competitors = competitor_df[competitor_df.industry == industry.industry][['companyLabel', 'companyLabelJA', 'company', 'country', 'countryLabel']].drop_duplicates().copy()
 			st.dataframe(competitors)
-			print("------")
+			# print("------")
 
 			st.title("Analysis by country")
 
@@ -176,30 +197,69 @@ if option == "By Company":
 				st.dataframe(competitors_by_country)
 
 
-		# st.title("Competitors per industry")
+elif option == "By Industry":
+
+	st.title("Searching by Industry")
+
+	# Get input
+	industry_input = st_keyup("Enter an industry name", value="retail", key="1", debounce=500)
+
+	# Perform search
+	industry_select_df = search_df(industry_input, industry_to_counts, 'industryLabel')
 
-		# for row in wikidata_industries.itertuples():
-		#    competitors = competitor_df[competitor_df.industry == row.industry][['companyLabel', 'companyLabelJA', 'company']].drop_duplicates()
-		#    st.write(f"For industry: {row.industryLabel}")
-		#    st.dataframe(competitors)
-		#    print("------")
+	# Show search results
+	with st.status("Searching ...", state="running", expanded=False) as status:
+		status.update(label=f"{len(industry_select_df)} results found", state="complete", expanded=True)
+
+		### Selection for Industry ###
+		st.dataframe(industry_select_df, on_select="rerun", key="industry", selection_mode="single-row")
+		select_industry = st.session_state.industry
 		
+		# expand if industry if selected
+		if len(select_industry['selection']['rows']) > 0:
 
-	##
+			industry_id = select_industry['selection']['rows'][0]
+			
+			industry = industry_select_df.iloc[industry_id]
 
-	# https://docs.streamlit.io/develop/api-reference/widgets/st.selectbox
+			st.title(f"All Competitors for {industry.industryLabel}")
+
+			competitors = competitor_df[competitor_df.industry == industry.industry][['companyLabel', 'companyLabelJA', 'company', 'country', 'countryLabel']].drop_duplicates().copy()
+			st.dataframe(competitors)
 
-	# company_input = st.selectbox(label="Company", options=unique_companies, placeholder="Choose a company")
 
-	# company_input = st.text_input("Company", "Enter company here")
 
-elif option == "By Industry":
-	
-	st.write("Industry search work in progress")
 
 elif option == "By Product":
 
-	st.write("Product search work in progress")
+	st.title("Searching by Product")
+
+	# Get input
+	product_input = st_keyup("Enter an product name", value="computer", key="2", debounce=500)
+
+	# Perform search
+	product_select_df = search_df(product_input, product_to_counts, 'productLabel')
+
+	# Show search results
+	with st.status("Searching ...", state="running", expanded=False) as status:
+		status.update(label=f"{len(product_select_df)} results found", state="complete", expanded=True)
+
+		### Selection for Product ###
+		st.dataframe(product_select_df, on_select="rerun", key="product", selection_mode="single-row")
+		select_product = st.session_state.product
+		
+		# expand if product if selected
+		if len(select_product['selection']['rows']) > 0:
+
+			product_id = select_product['selection']['rows'][0]
+			
+			product = product_select_df.iloc[product_id]
+
+			st.title(f"All Competitors for {product.productLabel}")
+
+			competitors = competitor_df[competitor_df['product'] == product['product']][['companyLabel', 'companyLabelJA', 'company', 'country', 'countryLabel']].drop_duplicates().copy()
+			st.dataframe(competitors)
+
 
 else: