Mohammed A

AI_ASSIST.md

@@ -2,18 +2,21 @@
 
 ## The prompt I gave
 
-<!-- Paste the exact prompt you gave the LLM here. -->
+<!-- How do I convert a Pandas column to datetime and replace invalid dates with missing values? -->
 
 ## The code it suggested
 
 ```python
-# Paste the relevant code the LLM suggested here.
+sales["date"] = pd.to_datetime(
+    sales["date"],
+    errors="coerce"
+)
 ```
 
 ## What I changed and why
 
-<!-- Describe what you kept, what you modified, and what you threw away. -->
+<!-- I used the suggested code exactly as provided. I applied it to the date column in the sales DataFrame during the cleaning step. Using errors="coerce" converts invalid dates to NaT, which made it easy to identify and remove rows containing invalid dates later in the pipeline. -->
 
 ## Did it work?
 
-<!-- Yes / partially / no — and what you learned from the interaction. -->
+<!-- Yes. The code successfully converted valid dates to the correct datetime format and replaced invalid dates with NaT. This simplified the data-cleaning process and showed how Pandas can handle date validation without writing custom parsing logic.-->

main.py

@@ -13,7 +13,7 @@
 OUTPUT_DIR = Path("output")
 
 # TODO (Task 7): replace with your GitHub username before running the pipeline.
-GITHUB_USERNAME = "<your-github-username>"
+GITHUB_USERNAME = "mohammedalfakih-dev"
 
 
 def run() -> None:

src/clean.py

@@ -6,23 +6,58 @@
 
 
 def load_and_explore(data_dir: Path) -> tuple[pd.DataFrame, pd.DataFrame]:
-    """Task 2: Load both CSV files and explore their contents before cleaning."""
-    # TODO: Read messy_sales.csv and messy_customers.csv with pd.read_csv().
-    # TODO: For each DataFrame call .info(), .describe(), .head(20), and .isna().sum().
-    # TODO: Log what you discover (e.g. which columns have nulls, any suspicious values).
-    raise NotImplementedError("Task 2: implement load_and_explore")
+    sales = pd.read_csv(data_dir / "messy_sales.csv")
+    customers = pd.read_csv(data_dir / "messy_customers.csv")
+
+    logging.info("=== SALES INFO ===")
+    sales.info()
+
+    logging.info("=== SALES DESCRIBE ===")
+    logging.info("\n%s", sales.describe(include="all"))
+
+    logging.info("=== SALES HEAD ===")
+    logging.info("\n%s", sales.head(20))
+
+    logging.info("=== SALES MISSING VALUES ===")
+    logging.info("\n%s", sales.isna().sum())
+
+    logging.info("=== CUSTOMERS INFO ===")
+    customers.info()
+
+    logging.info("=== CUSTOMERS DESCRIBE ===")
+    logging.info("\n%s", customers.describe(include="all"))
+
+    logging.info("=== CUSTOMERS HEAD ===")
+    logging.info("\n%s", customers.head(20))
+
+    logging.info("=== CUSTOMERS MISSING VALUES ===")
+    logging.info("\n%s", customers.isna().sum())
+
+    return sales, customers
 
 
 def clean_sales(sales: pd.DataFrame) -> pd.DataFrame:
     """Task 3: Clean the sales DataFrame using vectorized Pandas operations."""
-    # TODO: Normalize product_name with .str.strip().str.title().
-    # TODO: Normalize customer_email with .str.lower().str.strip().
-    # TODO: Convert price to numeric with pd.to_numeric(errors="coerce").
-    # TODO: Parse date with pd.to_datetime(errors="coerce").
-    # TODO: Drop rows where product_name is missing.
-    # TODO: Drop rows where price is negative.
-    # TODO: Drop rows where quantity is zero.
-    # TODO: Drop rows where date is NaT (invalid after parsing).
-    # TODO: Remove duplicate transactions: .drop_duplicates(subset="transaction_id", keep="first").
-    # TODO: Decide what to do with outlier prices (clip, flag, or leave) and add a comment explaining why.
-    raise NotImplementedError("Task 3: implement clean_sales")
+    sales = sales.copy()
+
+    sales["product_name"] = sales["product_name"].str.strip().str.title()
+    sales["customer_email"] = sales["customer_email"].str.lower().str.strip()
+    sales["price"] = pd.to_numeric(sales["price"], errors="coerce")
+    sales["date"] = pd.to_datetime(sales["date"], errors="coerce")
+
+    sales = sales[
+        sales["product_name"].notna()
+        & (sales["product_name"] != "")
+        & (sales["price"] >= 0)
+        & (sales["quantity"] != 0)
+        & sales["date"].notna()
+    ]
+
+    sales = sales.drop_duplicates(
+        subset="transaction_id",
+        keep="first",
+    )
+
+    logging.info("Cleaned sales rows: %s", len(sales))
+
+    return sales

src/ingest.py

@@ -14,21 +14,68 @@
 
 def download_inputs(data_dir: Path) -> None:
     """Task 1: Download input CSV files from Azure Blob Storage."""
-    # TODO: Create a BlobServiceClient using DefaultAzureCredential and ACCOUNT_URL.
-    # TODO: Get a container client for SOURCE_CONTAINER.
-    # TODO: For each filename in FILES, download the blob and write it to data_dir/<filename>.
-    # TODO: Log a message for each downloaded file.
-    raise NotImplementedError("Task 1: implement download_inputs")
+    data_dir.mkdir(exist_ok=True)
+
+    credential = DefaultAzureCredential()
+    service = BlobServiceClient(
+        account_url=ACCOUNT_URL,
+        credential=credential,
+    )
+
+    container = service.get_container_client(SOURCE_CONTAINER)
+
+    for filename in FILES:
+        blob = container.get_blob_client(filename)
+
+        with open(data_dir / filename, "wb") as f:
+            f.write(blob.download_blob().readall())
+
+        logging.info("Downloaded %s", filename)
 
 
 def upload_outputs(output_dir: Path, github_username: str) -> None:
     """Task 7 (extra credit): Upload Parquet outputs to Azure and verify the round-trip."""
     container_name = f"week4-{github_username}"
 
-    # EXTRA CREDIT — implement this after Tasks 2–6 are working.
-    # TODO: Create a BlobServiceClient using DefaultAzureCredential and ACCOUNT_URL.
-    # TODO: Get (or create) the container named container_name.
-    # TODO: Upload every .parquet file in output_dir to the container.
-    # TODO: Download customer_summary.parquet back and assert its row count matches the local file.
-    # TODO: Log the container name and number of files uploaded.
-    raise NotImplementedError("Task 7: implement upload_outputs")
+    credential = DefaultAzureCredential()
+    service = BlobServiceClient(
+        account_url=ACCOUNT_URL,
+        credential=credential,
+    )
+
+    container = service.get_container_client(container_name)
+
+    try:
+        container.create_container()
+        logging.info("Created container %s", container_name)
+    except Exception:
+        logging.info("Container %s already exists", container_name)
+
+    parquet_files = list(output_dir.glob("*.parquet"))
+
+    for path in parquet_files:
+        blob = container.get_blob_client(path.name)
+
+        with open(path, "rb") as f:
+            blob.upload_blob(f, overwrite=True)
+
+        logging.info("Uploaded %s", path.name)
+
+    local_customer_summary = pd.read_parquet(
+        output_dir / "customer_summary.parquet"
+    )
+
+    downloaded_bytes = container.get_blob_client(
+        "customer_summary.parquet"
+    ).download_blob().readall()
+
+    remote_customer_summary = pd.read_parquet(
+        io.BytesIO(downloaded_bytes)
+    )
+
+    assert len(local_customer_summary) == len(remote_customer_summary)
+
+    logging.info(
+        "Verified customer_summary.parquet row count: %s rows",
+        len(local_customer_summary),
+    )

src/report.py

@@ -2,30 +2,108 @@
 import logging
 from pathlib import Path
 
+import matplotlib
+matplotlib.use("Agg")
+
+import matplotlib.pyplot as plt
 import pandas as pd
 
 
 def build_reports(enriched: pd.DataFrame) -> dict[str, pd.DataFrame]:
     """Task 5: Build four summary tables using groupby and named aggregations."""
-    # TODO: Add a week column using .dt.isocalendar().week.
-    # TODO: Build weekly_revenue: group by week and region, columns week/region/total_revenue/order_count.
-    # TODO: Build customer_summary: group by customer_email, columns customer_email/customer_name/
-    #       region/loyalty_tier/total_spent/avg_order/order_count.
-    #       Use ("customer_name", "first") to pick the constant-per-group string columns.
-    # TODO: Build category_performance: group by category, columns category/total_revenue/order_count.
-    # TODO: Build loyalty_analysis: group by loyalty_tier, columns loyalty_tier/avg_spent/customer_count.
-    raise NotImplementedError("Task 5: implement build_reports")
+    enriched = enriched.copy()
+
+    enriched["revenue"] = enriched["price"] * enriched["quantity"]
+    enriched["week"] = enriched["date"].dt.isocalendar().week
+
+    weekly_revenue = (
+        enriched.groupby(["week", "region"])
+        .agg(
+            total_revenue=("revenue", "sum"),
+            order_count=("transaction_id", "count"),
+        )
+        .reset_index()
+    )
+
+    customer_summary = (
+        enriched.groupby("customer_email")
+        .agg(
+            customer_name=("customer_name", "first"),
+            region=("region", "first"),
+            loyalty_tier=("loyalty_tier", "first"),
+            total_spent=("revenue", "sum"),
+            avg_order=("revenue", "mean"),
+            order_count=("transaction_id", "count"),
+        )
+        .reset_index()
+    )
+
+    category_performance = (
+        enriched.groupby("category")
+        .agg(
+            total_revenue=("revenue", "sum"),
+            order_count=("transaction_id", "count"),
+        )
+        .reset_index()
+    )
+
+    loyalty_analysis = (
+        enriched.groupby("loyalty_tier")
+        .agg(
+            avg_spent=("revenue", "mean"),
+            customer_count=("customer_email", "nunique"),
+        )
+        .reset_index()
+    )
+
+    logging.info("Built report tables")
+
+    return {
+        "weekly_revenue": weekly_revenue,
+        "customer_summary": customer_summary,
+        "category_performance": category_performance,
+        "loyalty_analysis": loyalty_analysis,
+    }
 
 
 def write_outputs(reports: dict[str, pd.DataFrame], output_dir: Path) -> None:
     """Task 6: Write report tables to CSV/Parquet and save a bar chart."""
     output_dir.mkdir(exist_ok=True)
 
-    # TODO: Write reports["weekly_revenue"] to weekly_revenue.csv with index=False.
-    # TODO: Write reports["customer_summary"] to customer_summary.parquet with index=False.
-    # TODO: Write reports["category_performance"] to category_performance.csv with index=False.
-    # TODO: Sort category_performance by total_revenue descending.
-    # TODO: Plot a bar chart (x="category", y="total_revenue") and save to category_revenue.png
-    #       using plt.savefig(output_dir / "category_revenue.png", bbox_inches="tight").
-    #       Use matplotlib.use("Agg") before importing pyplot for headless environments.
-    raise NotImplementedError("Task 6: implement write_outputs")
+    reports["weekly_revenue"].to_csv(
+        output_dir / "weekly_revenue.csv",
+        index=False,
+    )
+
+    reports["customer_summary"].to_parquet(
+        output_dir / "customer_summary.parquet",
+        index=False,
+    )
+
+    reports["category_performance"].to_csv(
+        output_dir / "category_performance.csv",
+        index=False,
+    )
+
+    category_sorted = reports["category_performance"].sort_values(
+        "total_revenue",
+        ascending=False,
+    )
+
+    ax = category_sorted.plot(
+        kind="bar",
+        x="category",
+        y="total_revenue",
+        title="Revenue by category",
+    )
+
+    fig = ax.get_figure()
+
+    fig.savefig(
+        output_dir / "category_revenue.png",
+        bbox_inches="tight",
+    )
+
+    plt.close(fig)
+
+    logging.info("Output files written successfully")

src/transform.py

@@ -6,8 +6,20 @@
 
 def join_customers(sales: pd.DataFrame, customers: pd.DataFrame) -> pd.DataFrame:
     """Task 4: Normalize join keys, merge, and add a derived boolean flag."""
-    # TODO: Normalize customer_email in both DataFrames with .str.lower().str.strip().
-    # TODO: Merge sales with customers on customer_email using an inner join.
-    # TODO: Add a vectorized boolean column is_high_value: True where price * quantity >= 150.
-    # TODO: (Optional hands-on) Try a left join instead and inspect rows where customer_name is NaN.
-    raise NotImplementedError("Task 4: implement join_customers")
+    sales = sales.copy()
+    customers = customers.copy()
+
+    sales["customer_email"] = sales["customer_email"].str.lower().str.strip()
+    customers["customer_email"] = customers["customer_email"].str.lower().str.strip()
+
+    enriched = sales.merge(
+        customers,
+        on="customer_email",
+        how="inner",
+    )
+
+    enriched["is_high_value"] = enriched["price"] * enriched["quantity"] >= 150
+
+    logging.info("Rows after customer join: %s", len(enriched))
+
+    return enriched