From 2aa0ba4595ee8afef1ef1fca766dc4f1f9645b15 Mon Sep 17 00:00:00 2001
From: 6c4b0fdbf8f14f2bf5b4f27e84287421
 <6c4b0fdbf8f14f2bf5b4f27e84287421@app-learninglab.inria.fr>
Date: Sun, 12 Mar 2023 16:57:50 +0000
Subject: [PATCH] no commit message

---
 .../influenza-like-illness-analysis.ipynb     | 69 ++++++++-----------
 1 file changed, 28 insertions(+), 41 deletions(-)

diff --git a/module3/exo1/influenza-like-illness-analysis.ipynb b/module3/exo1/influenza-like-illness-analysis.ipynb
index d78c3cd..991ab68 100644
--- a/module3/exo1/influenza-like-illness-analysis.ipynb
+++ b/module3/exo1/influenza-like-illness-analysis.ipynb
@@ -2517,59 +2517,46 @@
     }
    ],
    "source": [
-    "%matplotlib inline\n",
-    "import matplotlib.pyplot as plt\n",
-    "import pandas as pd\n",
-    "import isoweek\n",
     "import os\n",
-    "import urllib\n",
+    "import urllib.request\n",
+    "import pandas as pd\n",
     "\n",
-    "data_file = \"incidence-PAY-3.csv\"\n",
-    "if not os.path.isfile(data_file):\n",
-    "    url = \"http://www.sentiweb.fr/datasets/incidence-PAY-3.csv\"\n",
-    "    urllib.request.urlretrieve(url, data_file)\n",
+    "# Define the URL for the data\n",
+    "url = 'https://raw.githubusercontent.com/MicrosoftDocs/mslearn-introduction-to-machine-learning/main/Data/ml-basics/crime.csv'\n",
     "\n",
-    "raw_data = pd.read_csv(data_file, skiprows=1)\n",
-    "raw_data[raw_data.isnull().any(axis=1)]\n",
+    "# Define the local filename\n",
+    "local_data_file = 'crime.csv'\n",
     "\n",
-    "data = raw_data.dropna().copy()\n",
+    "# If the local file doesn't exist, download the data and save to the local file\n",
+    "if not os.path.exists(local_data_file):\n",
+    "    urllib.request.urlretrieve(url, local_data_file)\n",
     "\n",
-    "def convert_week(year_and_week_int):\n",
-    "    year_and_week_str = str(year_and_week_int)\n",
-    "    year = int(year_and_week_str[:4])\n",
-    "    week = int(year_and_week_str[4:])\n",
-    "    w = isoweek.Week(year, week)\n",
-    "    return pd.Period(w.day(0), 'W')\n",
+    "# Read the data from the local file into a Pandas DataFrame\n",
+    "raw_data = pd.read_csv(local_data_file)\n",
     "\n",
-    "data['period'] = [convert_week(yw) for yw in data['week']]\n",
-    "sorted_data = data.set_index('period').sort_index()\n",
-    "periods = sorted_data.index\n",
+    "# Drop the first column, which contains the crime codes\n",
+    "data = raw_data.drop(columns=['Offence Code'])\n",
     "\n",
-    "for p1, p2 in zip(periods[:-1], periods[1:]):\n",
-    "    delta = p2.to_timestamp() - p1.end_time\n",
-    "    if delta > pd.Timedelta('1s'):\n",
-    "        print(p1, p2)\n",
+    "# Convert the 'Reported Date' column to a Pandas datetime type\n",
+    "data['Reported Date'] = pd.to_datetime(data['Reported Date'], format='%d/%m/%Y')\n",
     "\n",
-    "sorted_data['inc'].plot()\n",
-    "sorted_data['inc'][-200:].plot()\n",
-    "first_august_week = [pd.Period(pd.Timestamp(y, 8, 1), 'W')\n",
-    "                     for y in range(1985,\n",
-    "                                    sorted_data.index[-1].year)]\n",
-    "year = []\n",
-    "yearly_incidence = []\n",
+    "# Filter the data to include only the weeks of interest\n",
+    "data = data[(data['Reported Date'] >= '1989-05-01') & (data['Reported Date'] <= '1989-05-07') | \n",
+    "            (data['Reported Date'] >= '1989-05-15') & (data['Reported Date'] <= '1989-05-21')]\n",
     "\n",
-    "for week1, week2 in zip(first_august_week[:-1],\n",
-    "                        first_august_week[1:]):\n",
-    "    one_year = sorted_data['inc'][week1:week2-1]\n",
-    "    assert abs(len(one_year)-52) < 2\n",
-    "    yearly_incidence.append(one_year.sum())\n",
-    "    year.append(week2.year)\n",
-    "    \n",
-    "yearly_incidence = pd.Series(data=yearly_incidence, index=year)\n",
+    "# Compute the weekly crime incidence\n",
+    "weekly_incidence = data.groupby(pd.Grouper(key='Reported Date', freq='W')).size()\n",
+    "\n",
+    "# Compute the yearly crime incidence\n",
+    "yearly_incidence = weekly_incidence.groupby(weekly_incidence.index.year).sum()\n",
+    "year = yearly_incidence.index.astype(str)\n",
+    "yearly_incidence.index = year\n",
     "\n",
+    "# Plot the yearly crime incidence\n",
     "yearly_incidence.plot(style='*')\n",
     "yearly_incidence.sort_values()\n",
-    "yearly_incidence.hist(xrot=20)\n"
+    "yearly_incidence.hist(xrot=20)\n",
+    "\n"
    ]
   },
   {
-- 
2.18.1