Ellis
/
mailsys_differential_feature_extraction
ウォッチ 1
スター 0
フォーク 0
コード 課題 0 プルリクエスト 0 リリース 0 Wiki アクティビティ
ソースを参照

initial commit

master
Jeong Geol Kim 3年前
コミット
1e93fb07d6
5個のファイルの変更、2273行の追加、0行の削除
ユニファイド表示 差分情報を表示
  1. 143
    0
      module/coordsi.py
  2. 34
    0
      module/wavacc.py
  3. 32
    0
      script/createhandletrace.py
  4. 1384
    0
      toysnippet/cosinegraph.ipynb
  5. 680
    0
      toysnippet/sandbox.ipynb

+ 143
- 0
module/coordsi.py ファイルの表示

1 
+import os, sys
2 
+import pandas as pd
3 
+import numpy as np
4 
+import sklearn as sk
5 
+from sklearn import preprocessing
6 
+import math
7 
+'''
8 
+coordsi.py is a module for convert coordinates to SI unit.
9 
+
10 
+Warning: This module convert coordinates with heuristic method.
11 
+This moudle will be deprecated
12 
+'''
13 
+
14 
+def readCam (filepath):
15 
+    '''
16 
+    Create a dataframe from cam*.csv file.
17 
+    You must specify camera id. default is 1.
18 
+    '''
19 
+    try:
20 
+        df = pd.read_csv(filepath, header=0, dtype={'x': np.float64, 'y': np.float64, 'z': np.float64, 'frame': np.int64})
21 
+        return df
22 
+    except Exception as e:
23 
+        print(e)
24 
+
25 
+def summaryOriginCoord (root, camid=0):
26 
+    '''
27 
+    Show brief information of listed surgeon coordinate.
28 
+    '''
29 
+    d = root
30 
+    try:
31 
+        if camid == 1 or camid == 2 :
32 
+            df = pd.DataFrame(columns=['approx_total_frame', 'x_min', 'x_max', 'y_min', 'y_max', 'z_min', 'z_max'])
33 
+            subdirs = [x[0] for x in os.walk(d)]
34 
+            for d in subdirs[1:]:
35 
+                row = []
36 
+                #get a list of files in directory
37 
+                files = os.listdir(d)
38 
+                count_svo = len([s for s in files if "_1.csv" in s])
39 
+                filpath = os.path.join(d,'cam'+str(camid)+'.csv')
40 
+                if os.path.isfile(filpath):
41 
+                    arr = readCam(os.path.join(d,'cam'+str(camid)+'.csv'))
42 
+                    row = [3600 *count_svo, arr['x'].min(), arr['x'].max(), arr['y'].min(), arr['y'].max(), arr['z'].min(), arr['z'].max()]
43 
+                    df.loc[d] = row
44 
+                else:
45 
+                    print('Warning: '+filpath+' is not exist.')
46 
+                    continue
47 
+            return df
48 
+        else:
49 
+            print("Error: Camera ID must be 1 or 2. type camid=1 or camid=2 after dirpath")
50 
+    except Exception as e:
51 
+        print(e)
52 
+
53 
+
54 
+
55 
+
56 
+def convertToSI (origin, w, l, h):
57 
+    '''
58 
+    Waring: This function will be deprecated!
59 
+    Convert coordinates to SI unit with w, l, h.
60 
+    w, l, h are heuristic value. It will be changed after calibration and each surgeon room will geat unique value.
61 
+    '''
62 
+    try:
63 
+        df = origin.copy()
64 
+        #normailze dataframe[0] from -1 to 1
65 
+        df['x'] = preprocessing.minmax_scale(df['x'], feature_range=(-(w/2), (w/2)), axis=0, copy=True)
66 
+        #normailze dataframe[1] from -0.75 to 0.75
67 
+        df['y'] = preprocessing.minmax_scale(df['y'], feature_range=(-(l/2), (l/2)), axis=0, copy=True)
68 
+        #subtract dataframe[z] from int(4) and normailze from 0.93m to 1.8m (0 as floor)
69 
+        df['z'] = h - df['z']
70 
+        df['z'] = preprocessing.minmax_scale(df['z'], feature_range=(0.93,1.8), axis=0, copy=True)
71 
+        #change column order x, y to y, x
72 
+        df = df[['y', 'x', 'z', 'frame']]
73 
+        #change column name y to X, x to Y
74 
+        df = df.rename(columns={'y': 'x', 'x': 'y'})
75 
+        return df
76 
+    except Exception as e:
77 
+        print(e)
78 
+
79 
+def getVelocity (dataframe):
80 
+    try:
81 
+        df  = dataframe
82 
+        df['positionvectorvalue'] = (df['x']**2 + df['y']**2 + df['z']**2)
83 
+        buffer1, buffer2 = df['positionvectorvalue'].copy(), df['positionvectorvalue'].copy()
84 
+        buffer1, buffer2 = buffer1.to_frame(), buffer2.to_frame()
85 
+        buffer1, buffer2 = list(buffer1.loc[:, 'positionvectorvalue']), list(buffer2.loc[:, 'positionvectorvalue'])
86 
+        buffer3 = [0.0]
87 
+        for x in range(0, len(buffer2)-1):
88 
+            buffer3.append(buffer2[x])
89 
+        buffer3  = np.array(buffer1) - np.array(buffer3)
90 
+        for x in range(0, len(buffer3)):
91 
+            buffer3[x] = math.sqrt(abs(buffer3[x]))
92 
+        buffer3[0] = 0.0
93 
+        df['velocity'] = buffer3
94 
+        return df
95 
+    except Exception as e:
96 
+        print(e)
97 
+
98 
+def getAcceleration (dataframe):
99 
+    try:
100 
+        df = dataframe
101 
+        buffer1, buffer2 = df['velocity'].copy(), df['velocity'].copy()
102 
+        buffer1, buffer2 = buffer1.to_frame(), buffer2.to_frame()
103 
+        buffer1, buffer2 = list(buffer1.loc[:, 'velocity']), list(buffer2.loc[:, 'velocity'])
104 
+        buffer3 = [0.0]
105 
+        for x in range(0, len(buffer2)-1):
106 
+            buffer3.append(buffer2[x])
107 
+        buffer3  = np.array(buffer1) - np.array(buffer3)
108 
+        buffer3[1] = 0.0
109 
+        df['acceleration'] = buffer3
110 
+        return df
111 
+    except Exception as e:
112 
+        print(e)
113 
+
114 
+def getFullTrace (dataframe, approx_total_frame):
115 
+    try:
116 
+        df = dataframe
117 
+        total_frame = int(approx_total_frame)
118 
+        handletrace = pd.DataFrame(columns=['x', 'y', 'z', 'frame', 'positionvectorvalue', 'velocity', 'acceleration', 'isValid'])
119 
+        handletrace = pd.concat([handletrace, pd.DataFrame(np.zeros((total_frame,8)), columns=['x', 'y', 'z', 'frame', 'positionvectorvalue','velocity', 'acceleration', 'isValid'])], axis=0)
120 
+        for x in range(0, len(df)):
121 
+            handletrace.loc[df.loc[x, 'frame']] = df.loc[x]
122 
+        handletrace['isValid'] = handletrace['isValid'].fillna(0)
123 
+        return handletrace
124 
+    except Exception as e:
125 
+        print(e)
126 
+
127 
+def addValidDetection (dataframe, threshold = 25.0):
128 
+    '''
129 
+    threshold value is suitable for only 1st surgeon room(Seoul 801).
130 
+    We can make threshold in every surgeon room by using epipolar geometry.(but needs more cameras with different positions)
131 
+    '''
132 
+    try:
133 
+        df = dataframe
134 
+        top = threshold
135 
+        bottom = -threshold
136 
+        for x in range(0, len(df)):
137 
+            if bottom < df['acceleration'][x] < top:
138 
+                df['isValid'][x] = 1
139 
+            else:
140 
+                df['isValid'][x] = 0
141 
+        return df
142 
+    except Exception as e:
143 
+        print(e)

+ 34
- 0
module/wavacc.py ファイルの表示

1 
+import sys, os, math, time
2 
+import numpy as np
3 
+import pandas as pd
4 
+'''
5 
+wavacc.py for interpolate accelerometer data and extract feature as stroke.
6 
+Denosing step is not implemented this module. See addValidDetection function in coordsi.py for denoising.
7 
+'''
8 
+def interpolation(df):
9 
+    try:
10 
+        #implement data here
11 
+    except Exception as e:
12 
+        print(e)
13 
+        return df
14 
+
15 
+def decomposition(df):
16 
+    try:
17 
+        #implemnet decompositino with wavelet transform here
18 
+    except Exception as e:
19 
+        print(e)
20 
+        return df
21 
+
22 
+def getStroke(df):
23 
+    try:
24 
+        #implement get stroke here
25 
+    except Exception as e:
26 
+        print(e)
27 
+        return df
28 
+
29 
+def mergeToDataFrame(df):
30 
+    try:
31 
+        #implement merge to dataframe here
32 
+    except Exception as e:
33 
+        print(e)
34 
+        return df

+ 32
- 0
script/createhandletrace.py ファイルの表示

1 
+import os, sys
2 
+import pandas as pd
3 
+import numpy as np
4 
+import coordsi as csi
5 
+import math
6 
+import time
7 
+
8 
+# initialize root path
9 
+root = './List_Data_Call/'
10 
+
11 
+summary_1 = csi.summaryOriginCoord(root, camid=1)
12 
+
13 
+#make a loop for each index
14 
+for index, row in summary_1.iterrows():
15 
+    timestamp = []
16 
+    start_time = time.time()
17 
+    df = csi.readCam(os.path.join(index,'cam1.csv'))
18 
+    df = csi.convertToSI(df, 3.5, 1.5, 3.4)
19 
+    df = csi.getVelocity(df)
20 
+    df = csi.getAcceleration(df)
21 
+    df = csi.getFullTrace(df,row['approx_total_frame'] )
22 
+    df = csi.addValidDetection(df, 25.0)
23 
+    try:
24 
+        df.to_csv(os.path.join('./handletrace/', index[17:]+'.csv'), index=False)
25 
+    #save spend time and index of summary_1 in timestamp list
26 
+        timestamp.append([index, time.time() - start_time])
27 
+        print([index, time.time() - start_time])
28 
+    except Exception as e:
29 
+        print(e)
30 
+        continue
31 
+#save timestamp list to csv file
32 
+pd.DataFrame(timestamp, columns=['index', 'time']).to_csv('./handletrace/timestamp.csv', index=False)

+ 1384
- 0
toysnippet/cosinegraph.ipynb
ファイル差分が大きすぎるため省略します
ファイルの表示


+ 680
- 0
toysnippet/sandbox.ipynb ファイルの表示

1 
+{
2 
+ "cells": [
3 
+  {
4 
+   "cell_type": "code",
5 
+   "execution_count": 1,
6 
+   "metadata": {},
7 
+   "outputs": [],
8 
+   "source": [
9 
+    "import os, sys\n",
10 
+    "import pandas as pd\n",
11 
+    "import numpy as np\n",
12 
+    "import coordsi as csi\n",
13 
+    "import math\n",
14 
+    "import time"
15 
+   ]
16 
+  },
17 
+  {
18 
+   "attachments": {},
19 
+   "cell_type": "markdown",
20 
+   "metadata": {},
21 
+   "source": [
22 
+    "A brief summary of each original coordinate"
23 
+   ]
24 
+  },
25 
+  {
26 
+   "cell_type": "code",
27 
+   "execution_count": 2,
28 
+   "metadata": {},
29 
+   "outputs": [
30 
+    {
31 
+     "name": "stdout",
32 
+     "output_type": "stream",
33 
+     "text": [
34 
+      "Warning: ./List_Data_Call/21002290020230321/cam1.csv is not exist.\n",
35 
+      "                                    approx_total_frame  x_min   x_max  y_min   \n",
36 
+      "./List_Data_Call/21004038220221101            478800.0   -3.0  1900.0   -2.0  \\\n",
37 
+      "./List_Data_Call/21001264420230215            219600.0   -4.0  1901.0   -6.0   \n",
38 
+      "./List_Data_Call/21001555320230216            349200.0   -5.0  1884.0   -3.0   \n",
39 
+      "./List_Data_Call/21004030420221004            666000.0   -4.0  1902.0   -3.0   \n",
40 
+      "./List_Data_Call/21004008220221017            219600.0   -8.0  1883.0   -2.0   \n",
41 
+      "\n",
42 
+      "                                     y_max     z_min     z_max  \n",
43 
+      "./List_Data_Call/21004038220221101  1051.0  0.923129  4.137998  \n",
44 
+      "./List_Data_Call/21001264420230215  1055.0  0.953854  4.400389  \n",
45 
+      "./List_Data_Call/21001555320230216  1057.0  0.840809  3.938679  \n",
46 
+      "./List_Data_Call/21004030420221004  1057.0  0.933506  4.356071  \n",
47 
+      "./List_Data_Call/21004008220221017  1058.0  0.897373  4.207281  \n"
48 
+     ]
49 
+    }
50 
+   ],
51 
+   "source": [
52 
+    "# initialize root path\n",
53 
+    "root = './List_Data_Call/'\n",
54 
+    "\n",
55 
+    "summary_1 = csi.summaryOriginCoord(root, camid=1)\n",
56 
+    "print(summary_1.head())"
57 
+   ]
58 
+  },
59 
+  {
60 
+   "cell_type": "code",
61 
+   "execution_count": 3,
62 
+   "metadata": {},
63 
+   "outputs": [
64 
+    {
65 
+     "name": "stdout",
66 
+     "output_type": "stream",
67 
+     "text": [
68 
+      "./List_Data_Call/21004038220221101 64.0459258556366\n",
69 
+      "./List_Data_Call/21001264420230215 34.23401594161987\n",
70 
+      "./List_Data_Call/21001555320230216 55.52943301200867\n",
71 
+      "./List_Data_Call/21004030420221004 106.67347645759583\n",
72 
+      "./List_Data_Call/21004008220221017 31.72646999359131\n",
73 
+      "./List_Data_Call/21004056620230120 19.501684188842773\n",
74 
+      "./List_Data_Call/21001057620230126 53.51554536819458\n",
75 
+      "./List_Data_Call/21003885420220721 76.24831080436707\n",
76 
+      "./List_Data_Call/21004107920230313 97.09525084495544\n",
77 
+      "./List_Data_Call/21003975920220723 36.387489318847656\n",
78 
+      "./List_Data_Call/21004102020230228 31.510535717010498\n",
79 
+      "./List_Data_Call/21004036420221013 63.18059492111206\n",
80 
+      "./List_Data_Call/21003962420220712 36.284823179244995\n",
81 
+      "./List_Data_Call/21004048220221029 50.87060260772705\n",
82 
+      "./List_Data_Call/21003992420230119 49.36880159378052\n",
83 
+      "./List_Data_Call/21001418920220921 35.04419279098511\n",
84 
+      "./List_Data_Call/21004108620230225 94.45536732673645\n",
85 
+      "./List_Data_Call/21004095420230303 7.877222776412964\n",
86 
+      "./List_Data_Call/21003655120230207 22.74891757965088\n",
87 
+      "./List_Data_Call/21003817020230107 24.885369300842285\n",
88 
+      "./List_Data_Call/21003981020220923 36.27069091796875\n",
89 
+      "./List_Data_Call/21004033920221007 86.56228399276733\n",
90 
+      "./List_Data_Call/21004074720230104 37.52795934677124\n",
91 
+      "./List_Data_Call/21004037520230324 30.00572395324707\n",
92 
+      "./List_Data_Call/21004040420221103 90.27121639251709\n",
93 
+      "./List_Data_Call/21004026620221007 69.01991891860962\n",
94 
+      "./List_Data_Call/21001870620230315 39.85080003738403\n",
95 
+      "./List_Data_Call/21004068020230102 7.841302871704102\n",
96 
+      "./List_Data_Call/21004094420230206 100.37451100349426\n",
97 
+      "./List_Data_Call/21004097420230304 84.17479515075684\n",
98 
+      "./List_Data_Call/21004047820221028 89.44327425956726\n",
99 
+      "./List_Data_Call/21004051720230228 9.743078708648682\n",
100 
+      "./List_Data_Call/21004076520230204 76.26534867286682\n",
101 
+      "./List_Data_Call/21002591020230218 88.18855333328247\n",
102 
+      "./List_Data_Call/21004105820230311 59.186476945877075\n",
103 
+      "./List_Data_Call/21004037520230317 54.6233925819397\n",
104 
+      "./List_Data_Call/21003993520220917 95.81168413162231\n",
105 
+      "./List_Data_Call/21003967920220714 36.98200988769531\n",
106 
+      "./List_Data_Call/21004043620221025 25.73115038871765\n",
107 
+      "./List_Data_Call/21004097520230208 93.56520891189575\n",
108 
+      "./List_Data_Call/21004092020230127 89.9213137626648\n",
109 
+      "./List_Data_Call/21004026220220928 81.38130640983582\n"
110 
+     ]
111 
+    },
112 
+    {
113 
+     "ename": "ValueError",
114 
+     "evalue": "Found array with 0 sample(s) (shape=(0,)) while a minimum of 1 is required.",
115 
+     "output_type": "error",
116 
+     "traceback": [
117 
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
118 
+      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
119 
+      "Cell \u001b[0;32mIn[3], line 6\u001b[0m\n\u001b[1;32m      4\u001b[0m start_time \u001b[39m=\u001b[39m time\u001b[39m.\u001b[39mtime()\n\u001b[1;32m      5\u001b[0m df \u001b[39m=\u001b[39m csi\u001b[39m.\u001b[39mreadCam(os\u001b[39m.\u001b[39mpath\u001b[39m.\u001b[39mjoin(index,\u001b[39m'\u001b[39m\u001b[39mcam1.csv\u001b[39m\u001b[39m'\u001b[39m))\n\u001b[0;32m----> 6\u001b[0m df \u001b[39m=\u001b[39m csi\u001b[39m.\u001b[39;49mconvertToSI(df, \u001b[39m3.5\u001b[39;49m, \u001b[39m1.5\u001b[39;49m, \u001b[39m3.4\u001b[39;49m)\n\u001b[1;32m      7\u001b[0m df \u001b[39m=\u001b[39m csi\u001b[39m.\u001b[39mgetVelocity(df)\n\u001b[1;32m      8\u001b[0m df \u001b[39m=\u001b[39m csi\u001b[39m.\u001b[39mgetAcceleration(df)\n",
120 
+      "File \u001b[0;32m~/workspace/equation20/coordsi.py:62\u001b[0m, in \u001b[0;36mconvertToSI\u001b[0;34m(origin, w, l, h)\u001b[0m\n\u001b[1;32m     60\u001b[0m df \u001b[39m=\u001b[39m origin\u001b[39m.\u001b[39mcopy()\n\u001b[1;32m     61\u001b[0m \u001b[39m#normailze dataframe[0] from -1 to 1\u001b[39;00m\n\u001b[0;32m---> 62\u001b[0m df[\u001b[39m'\u001b[39m\u001b[39mx\u001b[39m\u001b[39m'\u001b[39m] \u001b[39m=\u001b[39m preprocessing\u001b[39m.\u001b[39;49mminmax_scale(df[\u001b[39m'\u001b[39;49m\u001b[39mx\u001b[39;49m\u001b[39m'\u001b[39;49m], feature_range\u001b[39m=\u001b[39;49m(\u001b[39m-\u001b[39;49m(w\u001b[39m/\u001b[39;49m\u001b[39m2\u001b[39;49m), (w\u001b[39m/\u001b[39;49m\u001b[39m2\u001b[39;49m)), axis\u001b[39m=\u001b[39;49m\u001b[39m0\u001b[39;49m, copy\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m)\n\u001b[1;32m     63\u001b[0m \u001b[39m#normailze dataframe[1] from -0.75 to 0.75\u001b[39;00m\n\u001b[1;32m     64\u001b[0m df[\u001b[39m'\u001b[39m\u001b[39my\u001b[39m\u001b[39m'\u001b[39m] \u001b[39m=\u001b[39m preprocessing\u001b[39m.\u001b[39mminmax_scale(df[\u001b[39m'\u001b[39m\u001b[39my\u001b[39m\u001b[39m'\u001b[39m], feature_range\u001b[39m=\u001b[39m(\u001b[39m-\u001b[39m(l\u001b[39m/\u001b[39m\u001b[39m2\u001b[39m), (l\u001b[39m/\u001b[39m\u001b[39m2\u001b[39m)), axis\u001b[39m=\u001b[39m\u001b[39m0\u001b[39m, copy\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m)\n",
121 
+      "File \u001b[0;32m~/.local/lib/python3.8/site-packages/sklearn/preprocessing/_data.py:624\u001b[0m, in \u001b[0;36mminmax_scale\u001b[0;34m(X, feature_range, axis, copy)\u001b[0m\n\u001b[1;32m    550\u001b[0m \u001b[39m\u001b[39m\u001b[39m\"\"\"Transform features by scaling each feature to a given range.\u001b[39;00m\n\u001b[1;32m    551\u001b[0m \n\u001b[1;32m    552\u001b[0m \u001b[39mThis estimator scales and translates each feature individually such\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    620\u001b[0m \u001b[39m<sphx_glr_auto_examples_preprocessing_plot_all_scaling.py>`.\u001b[39;00m\n\u001b[1;32m    621\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m    622\u001b[0m \u001b[39m# Unlike the scaler object, this function allows 1d input.\u001b[39;00m\n\u001b[1;32m    623\u001b[0m \u001b[39m# If copy is required, it will be done inside the scaler object.\u001b[39;00m\n\u001b[0;32m--> 624\u001b[0m X \u001b[39m=\u001b[39m check_array(\n\u001b[1;32m    625\u001b[0m     X, copy\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m, ensure_2d\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m, dtype\u001b[39m=\u001b[39;49mFLOAT_DTYPES, force_all_finite\u001b[39m=\u001b[39;49m\u001b[39m\"\u001b[39;49m\u001b[39mallow-nan\u001b[39;49m\u001b[39m\"\u001b[39;49m\n\u001b[1;32m    626\u001b[0m )\n\u001b[1;32m    627\u001b[0m original_ndim \u001b[39m=\u001b[39m X\u001b[39m.\u001b[39mndim\n\u001b[1;32m    629\u001b[0m \u001b[39mif\u001b[39;00m original_ndim \u001b[39m==\u001b[39m \u001b[39m1\u001b[39m:\n",
122 
+      "File \u001b[0;32m~/.local/lib/python3.8/site-packages/sklearn/utils/validation.py:931\u001b[0m, in \u001b[0;36mcheck_array\u001b[0;34m(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator, input_name)\u001b[0m\n\u001b[1;32m    929\u001b[0m     n_samples \u001b[39m=\u001b[39m _num_samples(array)\n\u001b[1;32m    930\u001b[0m     \u001b[39mif\u001b[39;00m n_samples \u001b[39m<\u001b[39m ensure_min_samples:\n\u001b[0;32m--> 931\u001b[0m         \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[1;32m    932\u001b[0m             \u001b[39m\"\u001b[39m\u001b[39mFound array with \u001b[39m\u001b[39m%d\u001b[39;00m\u001b[39m sample(s) (shape=\u001b[39m\u001b[39m%s\u001b[39;00m\u001b[39m) while a\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    933\u001b[0m             \u001b[39m\"\u001b[39m\u001b[39m minimum of \u001b[39m\u001b[39m%d\u001b[39;00m\u001b[39m is required\u001b[39m\u001b[39m%s\u001b[39;00m\u001b[39m.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    934\u001b[0m             \u001b[39m%\u001b[39m (n_samples, array\u001b[39m.\u001b[39mshape, ensure_min_samples, context)\n\u001b[1;32m    935\u001b[0m         )\n\u001b[1;32m    937\u001b[0m \u001b[39mif\u001b[39;00m ensure_min_features \u001b[39m>\u001b[39m \u001b[39m0\u001b[39m \u001b[39mand\u001b[39;00m array\u001b[39m.\u001b[39mndim \u001b[39m==\u001b[39m \u001b[39m2\u001b[39m:\n\u001b[1;32m    938\u001b[0m     n_features \u001b[39m=\u001b[39m array\u001b[39m.\u001b[39mshape[\u001b[39m1\u001b[39m]\n",
123 
+      "\u001b[0;31mValueError\u001b[0m: Found array with 0 sample(s) (shape=(0,)) while a minimum of 1 is required."
124 
+     ]
125 
+    }
126 
+   ],
127 
+   "source": [
128 
+    "#make a loop for each index\n",
129 
+    "for index, row in summary_1.iterrows():\n",
130 
+    "    timestamp = []\n",
131 
+    "    start_time = time.time()\n",
132 
+    "    df = csi.readCam(os.path.join(index,'cam1.csv'))\n",
133 
+    "    df = csi.convertToSI(df, 3.5, 1.5, 3.4)\n",
134 
+    "    df = csi.getVelocity(df)\n",
135 
+    "    df = csi.getAcceleration(df)\n",
136 
+    "    df = csi.getFullTrace(df,row['approx_total_frame'] )\n",
137 
+    "    df = csi.addValidDetection(df, 25.0)\n",
138 
+    "    df.to_csv(os.path.join('./handletrace/', index[17:]+'.csv'), index=False)\n",
139 
+    "    #save spend time and index of summary_1 in timestamp list    \n",
140 
+    "    timestamp.append([index, time.time() - start_time])\n",
141 
+    "#save timestamp list to csv file\n",
142 
+    "pd.DataFrame(timestamp, columns=['index', 'time']).to_csv('./handletrace/timestamp.csv', index=False)\n",
143 
+    "\n"
144 
+   ]
145 
+  },
146 
+  {
147 
+   "attachments": {},
148 
+   "cell_type": "markdown",
149 
+   "metadata": {},
150 
+   "source": [
151 
+    "import a origin coord and convert"
152 
+   ]
153 
+  },
154 
+  {
155 
+   "cell_type": "code",
156 
+   "execution_count": 3,
157 
+   "metadata": {},
158 
+   "outputs": [],
159 
+   "source": [
160 
+    "arr_1 = csi.readCam(os.path.join(summary_1.index[0],'cam1.csv'))\n",
161 
+    "si_1 = csi.convertToSI(arr_1, 3.5, 1.5, 3.4)\n",
162 
+    "#cartesian coordinate system\n",
163 
+    "#구면 좌표계로 변경도 해보자...나중에...\n",
164 
+    "#meter/(1/30)s\n",
165 
+    "si_1['positionvectorvalue'] = (si_1['x']**2 + si_1['y']**2 + si_1['z']**2)"
166 
+   ]
167 
+  },
168 
+  {
169 
+   "cell_type": "code",
170 
+   "execution_count": 4,
171 
+   "metadata": {},
172 
+   "outputs": [],
173 
+   "source": [
174 
+    "cal_buffer_1, cal_buffer_2 = si_1['positionvectorvalue'].copy(),  si_1['positionvectorvalue'].copy()\n",
175 
+    "#print(cal_buffer_1,'\\n',cal_buffer_2)\n",
176 
+    "cal_buffer_1, cal_buffer_2= cal_buffer_1.to_frame(), cal_buffer_2.to_frame()\n",
177 
+    "cal_buffer_1 = list(cal_buffer_1.loc[:, 'positionvectorvalue'])\n",
178 
+    "cal_buffer_2 = list(cal_buffer_2.loc[:, 'positionvectorvalue'])\n",
179 
+    "cal_buffer_3 = [0.0]\n",
180 
+    "for v in range(0, len(cal_buffer_2)-1):\n",
181 
+    "    cal_buffer_3.append(cal_buffer_2[v])\n",
182 
+    "buffer_a = np.array(cal_buffer_1)\n",
183 
+    "buffer_b = np.array(cal_buffer_3)"
184 
+   ]
185 
+  },
186 
+  {
187 
+   "cell_type": "code",
188 
+   "execution_count": 5,
189 
+   "metadata": {},
190 
+   "outputs": [],
191 
+   "source": [
192 
+    "velocity = (buffer_a - buffer_b)\n",
193 
+    "for x in range(0, len(velocity)):\n",
194 
+    "    velocity[x] = math.sqrt(abs(velocity[x]))\n",
195 
+    "velocity[0]=0.0"
196 
+   ]
197 
+  },
198 
+  {
199 
+   "cell_type": "code",
200 
+   "execution_count": 6,
201 
+   "metadata": {},
202 
+   "outputs": [],
203 
+   "source": [
204 
+    "#merge each list as Series\n",
205 
+    "si_1['velocity'] = velocity\n",
206 
+    "#print(si_1)"
207 
+   ]
208 
+  },
209 
+  {
210 
+   "cell_type": "code",
211 
+   "execution_count": 7,
212 
+   "metadata": {},
213 
+   "outputs": [],
214 
+   "source": [
215 
+    "cal_buffer_4, cal_buffer_5 = si_1['velocity'].copy(),  si_1['velocity'].copy()\n",
216 
+    "#print(cal_buffer_1,'\\n',cal_buffer_2)\n",
217 
+    "cal_buffer_4, cal_buffer_5= cal_buffer_4.to_frame(), cal_buffer_5.to_frame()\n",
218 
+    "cal_buffer_4 = list(cal_buffer_4.loc[:, 'velocity'])\n",
219 
+    "cal_buffer_5 = list(cal_buffer_5.loc[:, 'velocity'])\n",
220 
+    "cal_buffer_6 = [0.0]\n",
221 
+    "for v in range(0, len(cal_buffer_5)-1):\n",
222 
+    "    cal_buffer_6.append(cal_buffer_5[v])\n",
223 
+    "buffer_c = np.array(cal_buffer_4)\n",
224 
+    "buffer_d = np.array(cal_buffer_6)"
225 
+   ]
226 
+  },
227 
+  {
228 
+   "cell_type": "code",
229 
+   "execution_count": 8,
230 
+   "metadata": {},
231 
+   "outputs": [],
232 
+   "source": [
233 
+    "acceleration = buffer_c - buffer_d\n",
234 
+    "acceleration[1] = 0.0\n",
235 
+    "#print(acceleration)"
236 
+   ]
237 
+  },
238 
+  {
239 
+   "cell_type": "code",
240 
+   "execution_count": 9,
241 
+   "metadata": {},
242 
+   "outputs": [],
243 
+   "source": [
244 
+    "si_1['acceleration'] = acceleration\n",
245 
+    "#print(si_1)"
246 
+   ]
247 
+  },
248 
+  {
249 
+   "attachments": {},
250 
+   "cell_type": "markdown",
251 
+   "metadata": {},
252 
+   "source": [
253 
+    "Calculate Velocity of all detected objects"
254 
+   ]
255 
+  },
256 
+  {
257 
+   "attachments": {},
258 
+   "cell_type": "markdown",
259 
+   "metadata": {},
260 
+   "source": [
261 
+    "\n",
262 
+    "TODO: approx_total_frame 개수 만큼의 빈 컬럼 생성 (나중에 전체 데이터프레임은 20등분으로 잘릴 예정) -> done\n",
263 
+    "실제 값이 존재하는 프레임을 찾고, 그 프레임을 인덱스에 맞추어 x,y,z 집어넣기\n",
264 
+    "존재한다면 (x^2 + y^2 + z^2)^(1/3) 을 계산하여 새 컬럼에 저장\n",
265 
+    "비 등속 보간 작업을 해야 하는데, 어떤 방식으로 할지 결정하기(piecewise_polynomial?)"
266 
+   ]
267 
+  },
268 
+  {
269 
+   "cell_type": "code",
270 
+   "execution_count": 11,
271 
+   "metadata": {},
272 
+   "outputs": [
273 
+    {
274 
+     "data": {
275 
+      "text/html": [
276 
+       "<div>\n",
277 
+       "<style scoped>\n",
278 
+       "    .dataframe tbody tr th:only-of-type {\n",
279 
+       "        vertical-align: middle;\n",
280 
+       "    }\n",
281 
+       "\n",
282 
+       "    .dataframe tbody tr th {\n",
283 
+       "        vertical-align: top;\n",
284 
+       "    }\n",
285 
+       "\n",
286 
+       "    .dataframe thead th {\n",
287 
+       "        text-align: right;\n",
288 
+       "    }\n",
289 
+       "</style>\n",
290 
+       "<table border=\"1\" class=\"dataframe\">\n",
291 
+       "  <thead>\n",
292 
+       "    <tr style=\"text-align: right;\">\n",
293 
+       "      <th></th>\n",
294 
+       "      <th>x</th>\n",
295 
+       "      <th>y</th>\n",
296 
+       "      <th>z</th>\n",
297 
+       "      <th>frame</th>\n",
298 
+       "      <th>positionvectorvalue</th>\n",
299 
+       "      <th>velocity</th>\n",
300 
+       "      <th>acceleration</th>\n",
301 
+       "    </tr>\n",
302 
+       "  </thead>\n",
303 
+       "  <tbody>\n",
304 
+       "    <tr>\n",
305 
+       "      <th>count</th>\n",
306 
+       "      <td>62495.000000</td>\n",
307 
+       "      <td>62495.000000</td>\n",
308 
+       "      <td>62495.000000</td>\n",
309 
+       "      <td>62495.000000</td>\n",
310 
+       "      <td>62495.000000</td>\n",
311 
+       "      <td>62495.000000</td>\n",
312 
+       "      <td>62495.000000</td>\n",
313 
+       "    </tr>\n",
314 
+       "    <tr>\n",
315 
+       "      <th>mean</th>\n",
316 
+       "      <td>-0.202211</td>\n",
317 
+       "      <td>-0.207365</td>\n",
318 
+       "      <td>1.601385</td>\n",
319 
+       "      <td>42805.432355</td>\n",
320 
+       "      <td>2.733538</td>\n",
321 
+       "      <td>0.138262</td>\n",
322 
+       "      <td>0.000002</td>\n",
323 
+       "    </tr>\n",
324 
+       "    <tr>\n",
325 
+       "      <th>std</th>\n",
326 
+       "      <td>0.162759</td>\n",
327 
+       "      <td>0.238811</td>\n",
328 
+       "      <td>0.041177</td>\n",
329 
+       "      <td>27211.098449</td>\n",
330 
+       "      <td>0.162993</td>\n",
331 
+       "      <td>0.120752</td>\n",
332 
+       "      <td>0.124054</td>\n",
333 
+       "    </tr>\n",
334 
+       "    <tr>\n",
335 
+       "      <th>min</th>\n",
336 
+       "      <td>-0.750000</td>\n",
337 
+       "      <td>-1.750000</td>\n",
338 
+       "      <td>0.930000</td>\n",
339 
+       "      <td>1.000000</td>\n",
340 
+       "      <td>1.109630</td>\n",
341 
+       "      <td>0.000000</td>\n",
342 
+       "      <td>-1.650274</td>\n",
343 
+       "    </tr>\n",
344 
+       "    <tr>\n",
345 
+       "      <th>25%</th>\n",
346 
+       "      <td>-0.328348</td>\n",
347 
+       "      <td>-0.377956</td>\n",
348 
+       "      <td>1.574043</td>\n",
349 
+       "      <td>19851.500000</td>\n",
350 
+       "      <td>2.637680</td>\n",
351 
+       "      <td>0.067702</td>\n",
352 
+       "      <td>-0.045567</td>\n",
353 
+       "    </tr>\n",
354 
+       "    <tr>\n",
355 
+       "      <th>50%</th>\n",
356 
+       "      <td>-0.183048</td>\n",
357 
+       "      <td>-0.240016</td>\n",
358 
+       "      <td>1.598190</td>\n",
359 
+       "      <td>38725.000000</td>\n",
360 
+       "      <td>2.706999</td>\n",
361 
+       "      <td>0.111651</td>\n",
362 
+       "      <td>0.000205</td>\n",
363 
+       "    </tr>\n",
364 
+       "    <tr>\n",
365 
+       "      <th>75%</th>\n",
366 
+       "      <td>-0.096154</td>\n",
367 
+       "      <td>-0.032186</td>\n",
368 
+       "      <td>1.625495</td>\n",
369 
+       "      <td>69024.500000</td>\n",
370 
+       "      <td>2.793686</td>\n",
371 
+       "      <td>0.168573</td>\n",
372 
+       "      <td>0.045744</td>\n",
373 
+       "    </tr>\n",
374 
+       "    <tr>\n",
375 
+       "      <th>max</th>\n",
376 
+       "      <td>0.750000</td>\n",
377 
+       "      <td>1.750000</td>\n",
378 
+       "      <td>1.800000</td>\n",
379 
+       "      <td>233066.000000</td>\n",
380 
+       "      <td>6.039652</td>\n",
381 
+       "      <td>1.941675</td>\n",
382 
+       "      <td>1.692079</td>\n",
383 
+       "    </tr>\n",
384 
+       "  </tbody>\n",
385 
+       "</table>\n",
386 
+       "</div>"
387 
+      ],
388 
+      "text/plain": [
389 
+       "                  x             y             z          frame   \n",
390 
+       "count  62495.000000  62495.000000  62495.000000   62495.000000  \\\n",
391 
+       "mean      -0.202211     -0.207365      1.601385   42805.432355   \n",
392 
+       "std        0.162759      0.238811      0.041177   27211.098449   \n",
393 
+       "min       -0.750000     -1.750000      0.930000       1.000000   \n",
394 
+       "25%       -0.328348     -0.377956      1.574043   19851.500000   \n",
395 
+       "50%       -0.183048     -0.240016      1.598190   38725.000000   \n",
396 
+       "75%       -0.096154     -0.032186      1.625495   69024.500000   \n",
397 
+       "max        0.750000      1.750000      1.800000  233066.000000   \n",
398 
+       "\n",
399 
+       "       positionvectorvalue      velocity  acceleration  \n",
400 
+       "count         62495.000000  62495.000000  62495.000000  \n",
401 
+       "mean              2.733538      0.138262      0.000002  \n",
402 
+       "std               0.162993      0.120752      0.124054  \n",
403 
+       "min               1.109630      0.000000     -1.650274  \n",
404 
+       "25%               2.637680      0.067702     -0.045567  \n",
405 
+       "50%               2.706999      0.111651      0.000205  \n",
406 
+       "75%               2.793686      0.168573      0.045744  \n",
407 
+       "max               6.039652      1.941675      1.692079  "
408 
+      ]
409 
+     },
410 
+     "execution_count": 11,
411 
+     "metadata": {},
412 
+     "output_type": "execute_result"
413 
+    }
414 
+   ],
415 
+   "source": [
416 
+    "si_1.describe()"
417 
+   ]
418 
+  },
419 
+  {
420 
+   "cell_type": "code",
421 
+   "execution_count": 12,
422 
+   "metadata": {},
423 
+   "outputs": [
424 
+    {
425 
+     "name": "stdout",
426 
+     "output_type": "stream",
427 
+     "text": [
428 
+      "          x    y    z  frame  positionvectorvalue  velocity  acceleration   \n",
429 
+      "478795  0.0  0.0  0.0    0.0                  0.0       0.0           0.0  \\\n",
430 
+      "478796  0.0  0.0  0.0    0.0                  0.0       0.0           0.0   \n",
431 
+      "478797  0.0  0.0  0.0    0.0                  0.0       0.0           0.0   \n",
432 
+      "478798  0.0  0.0  0.0    0.0                  0.0       0.0           0.0   \n",
433 
+      "478799  0.0  0.0  0.0    0.0                  0.0       0.0           0.0   \n",
434 
+      "\n",
435 
+      "        isValid  \n",
436 
+      "478795      0.0  \n",
437 
+      "478796      0.0  \n",
438 
+      "478797      0.0  \n",
439 
+      "478798      0.0  \n",
440 
+      "478799      0.0  \n"
441 
+     ]
442 
+    }
443 
+   ],
444 
+   "source": [
445 
+    "# create dataframe with 6 columns and create 0 value rows as many as approx_total_frame value in summary_1\n",
446 
+    "j = 0\n",
447 
+    "handletrace = pd.DataFrame(columns=['x', 'y', 'z', 'frame', 'positionvectorvalue', 'velocity', 'acceleration', 'isValid'])\n",
448 
+    "handletrace = pd.concat([handletrace, pd.DataFrame(np.zeros((int(summary_1['approx_total_frame'][j]),8)), columns=['x', 'y', 'z', 'frame', 'positionvectorvalue','velocity', 'acceleration', 'isValid'])], axis=0)\n",
449 
+    "print(handletrace.tail())"
450 
+   ]
451 
+  },
452 
+  {
453 
+   "cell_type": "code",
454 
+   "execution_count": null,
455 
+   "metadata": {},
456 
+   "outputs": [],
457 
+   "source": [
458 
+    "#print(int(si_1['frame'][2]))\n",
459 
+    "#print(si_1.loc[2])"
460 
+   ]
461 
+  },
462 
+  {
463 
+   "cell_type": "code",
464 
+   "execution_count": 13,
465 
+   "metadata": {},
466 
+   "outputs": [],
467 
+   "source": [
468 
+    "# frame의 값에 해당하는 것으로 변경\n",
469 
+    "for x in range(0, len(si_1)):\n",
470 
+    "    handletrace.loc[int(si_1['frame'][x])] = si_1.loc[x]\n",
471 
+    "handletrace['isValid'] = handletrace['isValid'].fillna(0)"
472 
+   ]
473 
+  },
474 
+  {
475 
+   "cell_type": "code",
476 
+   "execution_count": 14,
477 
+   "metadata": {},
478 
+   "outputs": [
479 
+    {
480 
+     "name": "stdout",
481 
+     "output_type": "stream",
482 
+     "text": [
483 
+      "               x         y         z  frame  positionvectorvalue  velocity   \n",
484 
+      "0       0.000000  0.000000  0.000000    0.0             0.000000  0.000000  \\\n",
485 
+      "1      -0.400997 -0.319101  1.632182    1.0             2.926644  0.000000   \n",
486 
+      "2      -0.410969 -0.333815  1.629004    2.0             2.933981  0.085661   \n",
487 
+      "3      -0.412393 -0.352207  1.634730    3.0             2.966459  0.180214   \n",
488 
+      "4      -0.413818 -0.357725  1.638935    4.0             2.985322  0.137342   \n",
489 
+      "...          ...       ...       ...    ...                  ...       ...   \n",
490 
+      "478795  0.000000  0.000000  0.000000    0.0             0.000000  0.000000   \n",
491 
+      "478796  0.000000  0.000000  0.000000    0.0             0.000000  0.000000   \n",
492 
+      "478797  0.000000  0.000000  0.000000    0.0             0.000000  0.000000   \n",
493 
+      "478798  0.000000  0.000000  0.000000    0.0             0.000000  0.000000   \n",
494 
+      "478799  0.000000  0.000000  0.000000    0.0             0.000000  0.000000   \n",
495 
+      "\n",
496 
+      "        acceleration  isValid  \n",
497 
+      "0           0.000000      0.0  \n",
498 
+      "1           0.000000      0.0  \n",
499 
+      "2           0.000000      0.0  \n",
500 
+      "3           0.094553      0.0  \n",
501 
+      "4          -0.042873      0.0  \n",
502 
+      "...              ...      ...  \n",
503 
+      "478795      0.000000      0.0  \n",
504 
+      "478796      0.000000      0.0  \n",
505 
+      "478797      0.000000      0.0  \n",
506 
+      "478798      0.000000      0.0  \n",
507 
+      "478799      0.000000      0.0  \n",
508 
+      "\n",
509 
+      "[478800 rows x 8 columns]\n"
510 
+     ]
511 
+    }
512 
+   ],
513 
+   "source": [
514 
+    "print(handletrace)"
515 
+   ]
516 
+  },
517 
+  {
518 
+   "cell_type": "code",
519 
+   "execution_count": null,
520 
+   "metadata": {},
521 
+   "outputs": [],
522 
+   "source": [
523 
+    "'''import plotly.graph_objects as go\n",
524 
+    "\n",
525 
+    "#Create Figure\n",
526 
+    "fig = go.Figure()\n",
527 
+    "fig.add_trace(go.Scatter( x=list(handletrace.index), y=list(handletrace['velocity'] * 30)))\n",
528 
+    "\n",
529 
+    "#Set Title\n",
530 
+    "fig.update_layout(title_text='Velocity per second by frame')\n",
531 
+    "\n",
532 
+    "#Add range slider\n",
533 
+    "fig.update_layout(\n",
534 
+    "    xaxis=dict(\n",
535 
+    "        rangeslider=dict(\n",
536 
+    "            visible=True\n",
537 
+    "        )\n",
538 
+    "    )\n",
539 
+    ")'''"
540 
+   ]
541 
+  },
542 
+  {
543 
+   "cell_type": "code",
544 
+   "execution_count": null,
545 
+   "metadata": {},
546 
+   "outputs": [],
547 
+   "source": [
548 
+    "'''import plotly.graph_objects as go\n",
549 
+    "\n",
550 
+    "#Create Figure\n",
551 
+    "fig = go.Figure()\n",
552 
+    "fig.add_trace(go.Scatter( x=list(handletrace.index), y=list(handletrace['acceleration']*900)))\n",
553 
+    "\n",
554 
+    "#Set Title\n",
555 
+    "fig.update_layout(title_text='acceleration per second^2 by frame')\n",
556 
+    "\n",
557 
+    "#Add range slider\n",
558 
+    "fig.update_layout(\n",
559 
+    "    xaxis=dict(\n",
560 
+    "        rangeslider=dict(\n",
561 
+    "            visible=True\n",
562 
+    "        )\n",
563 
+    "    )\n",
564 
+    ")'''"
565 
+   ]
566 
+  },
567 
+  {
568 
+   "cell_type": "code",
569 
+   "execution_count": 15,
570 
+   "metadata": {},
571 
+   "outputs": [],
572 
+   "source": [
573 
+    "#comapre the value of handletrace['acceleration'] and if it is between -25 and 25, then set handletrace['isValid'] to 1\n",
574 
+    "for x in range(0, len(handletrace)):\n",
575 
+    "    if (-25/900) < handletrace['acceleration'][x] < (25/900):\n",
576 
+    "        handletrace['isValid'][x] = 1\n",
577 
+    "    else:\n",
578 
+    "        handletrace['isValid'][x] = 0"
579 
+   ]
580 
+  },
581 
+  {
582 
+   "cell_type": "code",
583 
+   "execution_count": 16,
584 
+   "metadata": {},
585 
+   "outputs": [
586 
+    {
587 
+     "name": "stdout",
588 
+     "output_type": "stream",
589 
+     "text": [
590 
+      "[1. 0.]\n",
591 
+      "isValid\n",
592 
+      "1.0    437730\n",
593 
+      "0.0     41070\n",
594 
+      "Name: count, dtype: int64\n"
595 
+     ]
596 
+    }
597 
+   ],
598 
+   "source": [
599 
+    "print(handletrace['isValid'].unique())\n",
600 
+    "print(handletrace['isValid'].value_counts())"
601 
+   ]
602 
+  },
603 
+  {
604 
+   "cell_type": "code",
605 
+   "execution_count": 17,
606 
+   "metadata": {},
607 
+   "outputs": [
608 
+    {
609 
+     "name": "stdout",
610 
+     "output_type": "stream",
611 
+     "text": [
612 
+      "               x         y         z  frame  positionvectorvalue  velocity   \n",
613 
+      "0       0.000000  0.000000  0.000000    0.0             0.000000  0.000000  \\\n",
614 
+      "1      -0.400997 -0.319101  1.632182    1.0             2.926644  0.000000   \n",
615 
+      "2      -0.410969 -0.333815  1.629004    2.0             2.933981  0.085661   \n",
616 
+      "3      -0.412393 -0.352207  1.634730    3.0             2.966459  0.180214   \n",
617 
+      "4      -0.413818 -0.357725  1.638935    4.0             2.985322  0.137342   \n",
618 
+      "...          ...       ...       ...    ...                  ...       ...   \n",
619 
+      "478795  0.000000  0.000000  0.000000    0.0             0.000000  0.000000   \n",
620 
+      "478796  0.000000  0.000000  0.000000    0.0             0.000000  0.000000   \n",
621 
+      "478797  0.000000  0.000000  0.000000    0.0             0.000000  0.000000   \n",
622 
+      "478798  0.000000  0.000000  0.000000    0.0             0.000000  0.000000   \n",
623 
+      "478799  0.000000  0.000000  0.000000    0.0             0.000000  0.000000   \n",
624 
+      "\n",
625 
+      "        acceleration  isValid  \n",
626 
+      "0           0.000000      1.0  \n",
627 
+      "1           0.000000      1.0  \n",
628 
+      "2           0.000000      1.0  \n",
629 
+      "3           0.094553      0.0  \n",
630 
+      "4          -0.042873      0.0  \n",
631 
+      "...              ...      ...  \n",
632 
+      "478795      0.000000      1.0  \n",
633 
+      "478796      0.000000      1.0  \n",
634 
+      "478797      0.000000      1.0  \n",
635 
+      "478798      0.000000      1.0  \n",
636 
+      "478799      0.000000      1.0  \n",
637 
+      "\n",
638 
+      "[478800 rows x 8 columns]\n"
639 
+     ]
640 
+    }
641 
+   ],
642 
+   "source": [
643 
+    "print(handletrace)"
644 
+   ]
645 
+  },
646 
+  {
647 
+   "cell_type": "code",
648 
+   "execution_count": null,
649 
+   "metadata": {},
650 
+   "outputs": [],
651 
+   "source": []
652 
+  }
653 
+ ],
654 
+ "metadata": {
655 
+  "kernelspec": {
656 
+   "display_name": "Python 3",
657 
+   "language": "python",
658 
+   "name": "python3"
659 
+  },
660 
+  "language_info": {
661 
+   "codemirror_mode": {
662 
+    "name": "ipython",
663 
+    "version": 3
664 
+   },
665 
+   "file_extension": ".py",
666 
+   "mimetype": "text/x-python",
667 
+   "name": "python",
668 
+   "nbconvert_exporter": "python",
669 
+   "pygments_lexer": "ipython3",
670 
+   "version": "3.8.0"
671 
+  },
672 
+  "vscode": {
673 
+   "interpreter": {
674 
+    "hash": "df0893f56f349688326838aaeea0de204df53a132722cbd565e54b24a8fec5f6"
675 
+   }
676 
+  }
677 
+ },
678 
+ "nbformat": 4,
679 
+ "nbformat_minor": 2
680 
+}

書き込み プレビュー
読み込み中…
キャンセル
保存