From 6b1bacd106e3229bc7ea2a762ee22a4238ab77f8 Mon Sep 17 00:00:00 2001
From: szpwski <szpwski@gmail.com>
Date: Mon, 3 Jan 2022 12:54:40 +0100
Subject: [PATCH] add sum of proximity
---
caly_kod.ipynb | 136 +++++++++++++++++++++++--------------------------
1 file changed, 65 insertions(+), 71 deletions(-)
diff --git a/caly_kod.ipynb b/caly_kod.ipynb
index 1c16446..2997511 100644
--- a/caly_kod.ipynb
+++ b/caly_kod.ipynb
@@ -3,7 +3,6 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "1d75aa04",
"metadata": {},
"outputs": [],
"source": [
@@ -20,13 +19,12 @@
{
"cell_type": "code",
"execution_count": 2,
- "id": "18dbc1d5",
"metadata": {},
"outputs": [],
"source": [
"params = urllib.parse.quote_plus(\"DRIVER={ODBC Driver 17 for SQL Server};\"\n",
- " \"SERVER=dbserver.mif.pg.gda.pl,1433;\"\n",
- " #\"SERVER=127.0.0.1,1433;\"\n",
+ " #\"SERVER=dbserver.mif.pg.gda.pl,1433;\"\n",
+ " \"SERVER=127.0.0.1,1433;\"\n",
" \"DATABASE=silkycoders;\"\n",
" \"UID=LOGIN;\"\n",
" \"PWD=HASLO\")\n",
@@ -36,8 +34,7 @@
},
{
"cell_type": "code",
- "execution_count": 24,
- "id": "15363396",
+ "execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@@ -59,8 +56,7 @@
},
{
"cell_type": "code",
- "execution_count": 25,
- "id": "0339aab0",
+ "execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
@@ -69,8 +65,7 @@
},
{
"cell_type": "code",
- "execution_count": 44,
- "id": "25a42792",
+ "execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
@@ -98,13 +93,14 @@
" dt[\"TIME_KMS\"] = np.floor(dt.TIME_MS/1000) \n",
" dt = dt.merge(dt.groupby(['EPC','TIME_KMS'])[\"PROXIMITY\"].max().reset_index(name=\"MAX_PROXIMITY_KMS\"), how=\"left\",\n",
" on = ['EPC','TIME_KMS'])\n",
+ " dt = dt.merge(dt.groupby(['EPC','TIME_KMS'])[\"PROXIMITY\"].sum().reset_index(name=\"SUM_PROXIMITY_KMS\"), how=\"left\",\n",
+ " on = ['EPC','TIME_KMS'])\n",
" return dt"
]
},
{
"cell_type": "code",
- "execution_count": 45,
- "id": "93baae83",
+ "execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
@@ -113,8 +109,7 @@
},
{
"cell_type": "code",
- "execution_count": 46,
- "id": "4204fa64",
+ "execution_count": 12,
"metadata": {},
"outputs": [
{
@@ -123,7 +118,7 @@
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"Int64Index: 502689 entries, 0 to 502688\n",
- "Data columns (total 35 columns):\n",
+ "Data columns (total 37 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 EPC 502689 non-null object \n",
@@ -158,11 +153,13 @@
" 29 TIME_MS 502689 non-null float64\n",
" 30 TIME_PER_MEASUREMENT_MS 502689 non-null float64\n",
" 31 NUMBER_OF_SIGNALS 502689 non-null int64 \n",
- " 32 LENGTH_OF_MEASUREMENT 502689 non-null int64 \n",
+ " 32 LENGTH_OF_MEASUREMENT 502689 non-null float64\n",
" 33 TIME_KMS 502689 non-null float64\n",
- " 34 MAX_PROXIMITY_KMS 502689 non-null float64\n",
- "dtypes: bool(1), float64(6), int32(4), int64(12), object(12)\n",
- "memory usage: 127.0+ MB\n"
+ " 34 MAX_PROXIMITY_KMS_x 502689 non-null float64\n",
+ " 35 MAX_PROXIMITY_KMS_y 502689 non-null float64\n",
+ " 36 SUM_PROXIMITY_KMS 502689 non-null float64\n",
+ "dtypes: bool(1), float64(9), int32(4), int64(11), object(12)\n",
+ "memory usage: 134.7+ MB\n"
]
}
],
@@ -172,8 +169,7 @@
},
{
"cell_type": "code",
- "execution_count": 47,
- "id": "05f9fc46",
+ "execution_count": 14,
"metadata": {},
"outputs": [
{
@@ -208,8 +204,6 @@
" <th>Size</th>\n",
" <th>SubclassID</th>\n",
" <th>...</th>\n",
- " <th>MIN</th>\n",
- " <th>SEC</th>\n",
" <th>MICROSEC</th>\n",
" <th>MILISEC</th>\n",
" <th>TIME_MS</th>\n",
@@ -217,7 +211,9 @@
" <th>NUMBER_OF_SIGNALS</th>\n",
" <th>LENGTH_OF_MEASUREMENT</th>\n",
" <th>TIME_KMS</th>\n",
- " <th>MAX_PROXIMITY_KMS</th>\n",
+ " <th>MAX_PROXIMITY_KMS_x</th>\n",
+ " <th>MAX_PROXIMITY_KMS_y</th>\n",
+ " <th>SUM_PROXIMITY_KMS</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
@@ -234,16 +230,16 @@
" <td>L</td>\n",
" <td>86</td>\n",
" <td>...</td>\n",
- " <td>46</td>\n",
- " <td>33</td>\n",
" <td>735000</td>\n",
" <td>35193735.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>9495</td>\n",
- " <td>103956</td>\n",
+ " <td>103956.0</td>\n",
" <td>0.0</td>\n",
" <td>-66.8</td>\n",
+ " <td>-66.8</td>\n",
+ " <td>-274.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
@@ -258,16 +254,16 @@
" <td>XS</td>\n",
" <td>630</td>\n",
" <td>...</td>\n",
- " <td>46</td>\n",
- " <td>33</td>\n",
" <td>747000</td>\n",
" <td>35193747.0</td>\n",
" <td>12.0</td>\n",
" <td>12.0</td>\n",
" <td>9495</td>\n",
- " <td>103956</td>\n",
+ " <td>103956.0</td>\n",
" <td>0.0</td>\n",
" <td>-60.8</td>\n",
+ " <td>-60.8</td>\n",
+ " <td>-244.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
@@ -282,16 +278,16 @@
" <td>M</td>\n",
" <td>11</td>\n",
" <td>...</td>\n",
- " <td>46</td>\n",
- " <td>33</td>\n",
" <td>751000</td>\n",
" <td>35193751.0</td>\n",
" <td>16.0</td>\n",
" <td>16.0</td>\n",
" <td>9495</td>\n",
- " <td>103956</td>\n",
+ " <td>103956.0</td>\n",
" <td>0.0</td>\n",
" <td>-74.4</td>\n",
+ " <td>-74.4</td>\n",
+ " <td>-300.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
@@ -306,16 +302,16 @@
" <td>XL</td>\n",
" <td>82</td>\n",
" <td>...</td>\n",
- " <td>46</td>\n",
- " <td>33</td>\n",
" <td>754000</td>\n",
" <td>35193754.0</td>\n",
" <td>19.0</td>\n",
" <td>19.0</td>\n",
" <td>9495</td>\n",
- " <td>103956</td>\n",
+ " <td>103956.0</td>\n",
" <td>0.0</td>\n",
" <td>-78.0</td>\n",
+ " <td>-78.0</td>\n",
+ " <td>-318.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
@@ -330,20 +326,20 @@
" <td>38</td>\n",
" <td>53</td>\n",
" <td>...</td>\n",
- " <td>46</td>\n",
- " <td>33</td>\n",
" <td>758000</td>\n",
" <td>35193758.0</td>\n",
" <td>23.0</td>\n",
" <td>23.0</td>\n",
" <td>9495</td>\n",
- " <td>103956</td>\n",
+ " <td>103956.0</td>\n",
" <td>0.0</td>\n",
" <td>-71.1</td>\n",
+ " <td>-71.1</td>\n",
+ " <td>-214.1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
- "<p>5 rows Ă 35 columns</p>\n",
+ "<p>5 rows Ă 37 columns</p>\n",
"</div>"
],
"text/plain": [
@@ -354,43 +350,49 @@
"3 30356847541DA78000B5BA4D -78.0 2021-10-26T09:46:33.754 1 \n",
"4 30356847542A2B0000B5B215 -71.1 2021-10-26T09:46:33.758 1 \n",
"\n",
- " ITEMID EAN StyleColorSize StyleColor Size SubclassID ... MIN \\\n",
- "0 2127269 5902805533040 RH267-85J-L RH267-85J L 86 ... 46 \n",
- "1 2217401 5902851445731 RS483-99X-XS RS483-99X XS 630 ... 46 \n",
- "2 2227511 5902851547602 SB281-90M-M SB281-90M M 11 ... 46 \n",
- "3 2104706 5902805303667 RJ369-87X-XL RJ369-87X XL 82 ... 46 \n",
- "4 2117629 5902805431803 RM119-93X-38 RM119-93X 38 53 ... 46 \n",
+ " ITEMID EAN StyleColorSize StyleColor Size SubclassID ... \\\n",
+ "0 2127269 5902805533040 RH267-85J-L RH267-85J L 86 ... \n",
+ "1 2217401 5902851445731 RS483-99X-XS RS483-99X XS 630 ... \n",
+ "2 2227511 5902851547602 SB281-90M-M SB281-90M M 11 ... \n",
+ "3 2104706 5902805303667 RJ369-87X-XL RJ369-87X XL 82 ... \n",
+ "4 2117629 5902805431803 RM119-93X-38 RM119-93X 38 53 ... \n",
+ "\n",
+ " MICROSEC MILISEC TIME_MS TIME_PER_MEASUREMENT_MS NUMBER_OF_SIGNALS \\\n",
+ "0 735000 35193735.0 0.0 0.0 9495 \n",
+ "1 747000 35193747.0 12.0 12.0 9495 \n",
+ "2 751000 35193751.0 16.0 16.0 9495 \n",
+ "3 754000 35193754.0 19.0 19.0 9495 \n",
+ "4 758000 35193758.0 23.0 23.0 9495 \n",
"\n",
- " SEC MICROSEC MILISEC TIME_MS TIME_PER_MEASUREMENT_MS \\\n",
- "0 33 735000 35193735.0 0.0 0.0 \n",
- "1 33 747000 35193747.0 12.0 12.0 \n",
- "2 33 751000 35193751.0 16.0 16.0 \n",
- "3 33 754000 35193754.0 19.0 19.0 \n",
- "4 33 758000 35193758.0 23.0 23.0 \n",
+ " LENGTH_OF_MEASUREMENT TIME_KMS MAX_PROXIMITY_KMS_x MAX_PROXIMITY_KMS_y \\\n",
+ "0 103956.0 0.0 -66.8 -66.8 \n",
+ "1 103956.0 0.0 -60.8 -60.8 \n",
+ "2 103956.0 0.0 -74.4 -74.4 \n",
+ "3 103956.0 0.0 -78.0 -78.0 \n",
+ "4 103956.0 0.0 -71.1 -71.1 \n",
"\n",
- " NUMBER_OF_SIGNALS LENGTH_OF_MEASUREMENT TIME_KMS MAX_PROXIMITY_KMS \n",
- "0 9495 103956 0.0 -66.8 \n",
- "1 9495 103956 0.0 -60.8 \n",
- "2 9495 103956 0.0 -74.4 \n",
- "3 9495 103956 0.0 -78.0 \n",
- "4 9495 103956 0.0 -71.1 \n",
+ " SUM_PROXIMITY_KMS \n",
+ "0 -274.6 \n",
+ "1 -244.2 \n",
+ "2 -300.2 \n",
+ "3 -318.9 \n",
+ "4 -214.1 \n",
"\n",
- "[5 rows x 35 columns]"
+ "[5 rows x 37 columns]"
]
},
- "execution_count": 47,
+ "execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "df.head()"
+ "df[df.MEASUREMENT == 1].head()"
]
},
{
"cell_type": "code",
"execution_count": 88,
- "id": "6b4cd796",
"metadata": {},
"outputs": [
{
@@ -614,7 +616,6 @@
{
"cell_type": "code",
"execution_count": 67,
- "id": "362630f1",
"metadata": {},
"outputs": [
{
@@ -903,7 +904,6 @@
},
{
"cell_type": "markdown",
- "id": "b01e5c4c",
"metadata": {},
"source": [
"## EDA"
@@ -912,7 +912,6 @@
{
"cell_type": "code",
"execution_count": 125,
- "id": "fb8764f0",
"metadata": {},
"outputs": [
{
@@ -936,7 +935,6 @@
{
"cell_type": "code",
"execution_count": 123,
- "id": "5bd6b37a",
"metadata": {},
"outputs": [
{
@@ -961,7 +959,6 @@
{
"cell_type": "code",
"execution_count": 126,
- "id": "f796d170",
"metadata": {},
"outputs": [
{
@@ -985,7 +982,6 @@
{
"cell_type": "code",
"execution_count": 127,
- "id": "4fcb7ddf",
"metadata": {},
"outputs": [
{
@@ -1009,7 +1005,6 @@
{
"cell_type": "code",
"execution_count": 144,
- "id": "4cbcf0eb",
"metadata": {},
"outputs": [
{
@@ -1038,7 +1033,6 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "3039f4ab",
"metadata": {},
"outputs": [],
"source": []
@@ -1060,7 +1054,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.8.8"
+ "version": "3.8.3"
}
},
"nbformat": 4,
--
GitLab