Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 35 additions & 0 deletions SQL lab 7.ipynb
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
{
"metadata": {
"kernelspec": {
"name": "python",
"display_name": "Python (Pyodide)",
"language": "python"
},
"language_info": {
"codemirror_mode": {
"name": "python",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8"
}
},
"nbformat_minor": 5,
"nbformat": 4,
"cells": [
{
"id": "6c0a67d3-de8f-4b6a-b51d-9fe737ee5ab3",
"cell_type": "code",
"source": "import pandas as pd\nfrom sqlalchemy import create_engine\nimport getpass\n\npassword = getpass.getpass(\"Enter MySQL password: \")\nuser = \"root\"\nhost = \"localhost\"\ndb = \"sakila\"\n\nconnection_string = f\"mysql+pymysql://{user}:{password}@{host}/{db}\"\nengine = create_engine(connection_string)\n\nwith engine.connecction() as conn:\n print(\"Connection successfully!\")\n\ndef rentals_month(engine, month, year):\n query = f\"\"\"\n SELECT *\n FROM rental\n WHERE MONTH(rental_date) = {month}\n AND YEAR(rental_date) = {year}\n \"\"\"\n df = pd.read_sql(query, engine)\n return df\n\ndef rental_count_month(df, month, year):\n col_name = f\"rentals_{month:02d}_{year}\"\n\n result = (\n df.groupby(\"customer_id\")\n .size()\n .reset_index(name=col_name)\n )\n return result\n\ndef compare_rentals(df1, df2):\n combined = pd.merge(df1, df2, on=\"customer_id\", how=\"outer\")\n combined = combined.fillna(0)\n\n rental_cols = [c for c in combined.columns if c != \"customer_id\"]\n combined[\"difference\"] = combined[rental_cols[0]] - combined[rental_cols[1]]\n\n return combined\n\nmay_df = rentals_month(engine, 5, 2005)\njune_df = rentals_month(engine, 6, 2005)\n\nmay_counts = rental_count_month(may_df, 5, 2005)\njune_counts = rental_count_month(june_df, 6,2005)\n\ncomparison = compare_rentals(may_counts, june_counts)\ncomparison.head()",
"metadata": {
"trusted": true
},
"outputs": [],
"execution_count": null
}
]
}