Felipe Zanluca - Data Challenge Solution

.gitignore

@@ -0,0 +1,23 @@
+#venv
+.venv/
+
+# Env variables
+.env
+
+#PyCharm
+.idea/
+
+#Notes
+.notes
+
+#Python cache
+__pycache__/
+*.py[cod]
+
+#Development follow-up
+DEVELOPMENT.md
+
+#Personal Documentation
+querys.sql
+looqbox_data_challenge_felipe_zanluca.odt
+looqbox_data_challenge_felipe_zanluca.pdf

requirements.txt

@@ -0,0 +1,15 @@
+contourpy==1.3.3
+cycler==0.12.1
+fonttools==4.63.0
+kiwisolver==1.5.0
+matplotlib==3.11.0
+mysql-connector-python==9.7.0
+numpy==2.5.0
+packaging==26.2
+pandas==3.0.3
+pandas-stubs==3.0.3.260530
+pillow==12.2.0
+pyparsing==3.3.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.2.2
+six==1.17.0

sql/question1.sql

@@ -0,0 +1,9 @@
+-- What are the 10 most expensive products in the company?
+SELECT
+    PRODUCT_COD
+    ,PRODUCT_NAME
+    ,PRODUCT_VAL
+FROM data_product
+WHERE PRODUCT_VAL IS NOT NULL
+ORDER BY PRODUCT_VAL DESC
+LIMIT 10;

sql/question2.sql

@@ -0,0 +1,9 @@
+-- What sections do the 'BEBIDAS' and 'PADARIA' departments have?
+SELECT DISTINCT
+    DEP_COD
+    ,DEP_NAME
+    ,SECTION_COD
+    ,SECTION_NAME
+FROM data_product
+WHERE DEP_NAME IN ('BEBIDAS','PADARIA')
+ORDER BY DEP_NAME, SECTION_NAME

sql/question3.sql

@@ -0,0 +1,50 @@
+-- What was the total sale of products (in $) of each Business Area in the first quarter of 2019?
+
+SELECT
+    cd.BUSINESS_NAME
+    ,SUM(sl.SALES_VALUE) AS SALES_VALUE
+FROM data_store_sales sl
+LEFT JOIN data_store_cad cd
+ON sl.STORE_CODE = cd.STORE_CODE
+WHERE sl.DATE BETWEEN '2019-01-01' AND '2019-03-31'
+GROUP BY
+    cd.BUSINESS_NAME
+
+
+/*
+Exploratory analysis:
+
+1.Daily sales by Business Area during Q1 2019.
+
+SELECT
+    cd.BUSINESS_NAME
+    ,SUM(sl.SALES_VALUE) AS SALES_VALUE
+    ,sl.DATE
+FROM data_store_sales sl
+LEFT JOIN data_store_cad cd
+ON sl.STORE_CODE = cd.STORE_CODE
+WHERE sl.DATE BETWEEN '2019-01-01' AND '2019-03-31'
+GROUP BY
+    cd.BUSINESS_NAME
+    ,sl.DATE
+;
+
+2.Monthly sales aggregation by Business Area during Q1 2019.
+
+SELECT
+    cd.BUSINESS_NAME
+    ,SUM(sl.SALES_VALUE) AS SALES_VALUE
+    ,CASE WHEN
+        MONTH(sl.DATE) = 1 THEN 'Jan'
+        WHEN MONTH(sl.DATE) = 2 THEN 'Feb'
+        ELSE 'Mar'
+    END AS MONTH
+FROM data_store_sales sl
+LEFT JOIN data_store_cad cd
+ON sl.STORE_CODE = cd.STORE_CODE
+WHERE sl.DATE BETWEEN '2019-01-01' AND '2019-03-31'
+GROUP BY
+    cd.BUSINESS_NAME
+    ,MONTH
+;
+ */

src/database.py

@@ -0,0 +1,28 @@
+import os
+
+import mysql.connector as sql
+from mysql.connector import Error
+from dotenv import load_dotenv
+
+load_dotenv()
+
+
+# Connection
+def get_connection():
+    try:
+        return sql.connect(
+            host=os.getenv("MYSQL_HOST"),
+            user=os.getenv("MYSQL_USER"),
+            password=os.getenv("MYSQL_PASSWORD"),
+            database=os.getenv("MYSQL_DATABASE"),
+        )
+    except Error as e:
+        print(f"Connection error: {e}")
+        raise
+
+
+if __name__ == "__main__":
+    conn = get_connection()
+    if conn.is_connected():
+        print(f"Success! Connected to {conn.server_info}")
+    conn.close()

src/explore_database.py

@@ -0,0 +1,49 @@
+import pandas as pd
+
+pd.set_option("display.max_columns", None)
+pd.set_option("display.width", None)
+
+from database import get_connection
+
+def explore_table(table):
+    connection = get_connection()
+
+    try:
+        print("\n" + "=" * 60)
+        print(f"TABLE: {table}")
+        print("=" * 60)
+
+        describe = pd.read_sql(
+            f"DESCRIBE {table}",
+            connection
+        )
+        print(describe)
+
+        print("\n" + "=" * 60)
+        print("SAMPLE:")
+
+        sample = pd.read_sql(
+            f"SELECT * FROM {table} LIMIT 5",
+            connection
+        )
+        print(sample)
+
+    finally:
+        connection.close()
+
+
+def explore_tables(tables):
+    for table in tables:
+        explore_table(table)
+
+
+if __name__ == "__main__":
+    tables = [
+        "IMDB_movies",
+        "data_product",
+        "data_product_sales",
+        "data_store_cad",
+        "data_store_sales"
+    ]
+
+    explore_tables(tables)

src/imdb_visualization.py

@@ -0,0 +1,82 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import database as db
+
+
+def load_imdb_movies():
+    connection = db.get_connection()
+    try:
+        query = """
+                SELECT *
+                FROM IMDB_movies
+                """
+        df = pd.read_sql(query, connection)
+        return df
+    finally:
+        connection.close()
+
+
+def plot_top10_movies_by_metascore():
+    movies_df = load_imdb_movies()
+    print("Generating Metascore bar chart...")
+    top_10 = (
+        movies_df
+        .dropna(subset=["Metascore"])
+        .sort_values(by=["Metascore", "Votes"],
+                     ascending=[False, False]
+                     ).head(10)
+    )
+
+    chart_data = top_10.set_index("Title")["Metascore"]
+
+    plt.figure(figsize=(10, 10))
+    ax = chart_data.sort_values(ascending=True).plot(kind="barh")
+    ax.bar_label(ax.containers[0], fmt="%.0f", padding=3)
+    plt.title('Top 10 movies by Metascore')
+    plt.xlabel("Metascore")
+    plt.ylabel("Title")
+    plt.tight_layout()
+    plt.savefig("top10_movies_by_metascore.png", dpi=300,bbox_inches="tight")
+    plt.show()
+    plt.close()
+
+
+def plot_scatter_revenue_metascore():
+    movies_df = load_imdb_movies()
+    print("Generating Revenue vs Metascore scatter plot...")
+    scatter_df = movies_df[["Title", "RevenueMillions", "Metascore"]].copy()
+    print(f"Original dataset shape: {movies_df.shape}")
+
+    scatter_df = scatter_df.dropna(
+        subset=["RevenueMillions", "Metascore"]
+    )
+    scatter_df = scatter_df[
+        scatter_df["RevenueMillions"] > 0
+    ]
+
+    print(f"Cleaned scatter dataset shape: {scatter_df.shape}")
+
+    plt.figure(figsize=(10, 8))
+    plt.scatter(
+        scatter_df["RevenueMillions"],
+        scatter_df["Metascore"],
+        alpha=0.6
+    )
+    # Log scale improves readability because revenue values are highly spread out.
+    plt.xscale("log")
+
+    plt.title("Revenue vs Metascore")
+    plt.xlabel("Revenue in millions (log scale)")
+    plt.ylabel("Metascore")
+    plt.tight_layout()
+    plt.savefig("revenue_vs_metascore.png", dpi=300,bbox_inches="tight")
+    plt.show()
+    plt.close()
+
+
+if __name__ == '__main__':
+    # Top 10 movies by Metascore
+    plot_top10_movies_by_metascore()
+
+    # Relationship between Revenue and Metascore
+    plot_scatter_revenue_metascore()

src/retrieve_data.py

@@ -0,0 +1,47 @@
+import pandas as pd
+import database as db
+
+
+def retrieve_data(product_code: int = None, store_code: int = None, date=None):
+    connection = db.get_connection()
+
+    try:
+        query = """
+                SELECT *
+                FROM data_product_sales
+                """
+
+        conditions = []
+        params = []
+
+        if product_code is not None:
+            conditions.append("PRODUCT_CODE = %s")
+            params.append(product_code)
+
+        if store_code is not None:
+            conditions.append("STORE_CODE = %s")
+            params.append(store_code)
+
+        if date is not None and len(date) != 2:
+            raise ValueError("Date should be a list with two elements")
+
+        if date is not None:
+            conditions.append("DATE BETWEEN %s AND %s")
+            params.extend([date[0], date[1]])
+
+        if conditions:
+            query += " WHERE " + " AND ".join(conditions)
+
+        result = pd.read_sql(query, connection, params=params)
+        return result
+
+    finally:
+        connection.close()
+
+
+if __name__ == "__main__":
+    my_data = retrieve_data(
+        product_code=172,
+        store_code=2
+    )
+    print(my_data)