fix problem for df drop

4951f96e · Francesco Santanastasio · 8fe74ecf · 4951f96e
Commit 4951f96e authored 10 months ago by Francesco Santanastasio
--- a/TestCarrello.ipynb
+++ b/TestCarrello.ipynb
@@ -10,7 +10,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 1,
   "id": "7d6638fa",
   "metadata": {},
   "outputs": [],
@@ -30,7 +30,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 2,
   "id": "28e10b83",
   "metadata": {},
   "outputs": [],
@@ -52,7 +52,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 3,
   "id": "913eb5c9",
   "metadata": {},
   "outputs": [
@@ -159,7 +159,7 @@
       "[119 rows x 2 columns]"
      ]
     },
-     "execution_count": 45,
+     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -171,7 +171,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 4,
   "id": "f5f6e2b1",
   "metadata": {},
   "outputs": [
@@ -278,7 +278,7 @@
       "[119 rows x 2 columns]"
      ]
     },
-     "execution_count": 46,
+     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -291,7 +291,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 5,
   "id": "033725f4",
   "metadata": {},
   "outputs": [
@@ -301,7 +301,7 @@
       "<AxesSubplot:xlabel='t'>"
      ]
     },
-     "execution_count": 47,
+     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
@@ -325,7 +325,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 7,
   "id": "36271ccd",
   "metadata": {},
   "outputs": [
@@ -337,14 +337,6 @@
      "Numero misure (dopo i tagli):  60\n"
     ]
    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/var/folders/ws/ytnwy3cs0hz8z73rvtwydngm0000gn/T/ipykernel_40871/1233098160.py:3: FutureWarning: Index.__or__ operating as a set operation is deprecated, in the future this will be a logical operation matching Series.__or__.  Use index.union(other) instead\n",
-      "  df_new = df.drop(df[df.t <2 ].index | df[df.t > 5].index)\n"
-     ]
-    },
    {
     "data": {
      "text/html": [
@@ -739,7 +731,7 @@
       "98  4.9695  0.009586"
      ]
     },
-     "execution_count": 55,
+     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -747,14 +739,16 @@
   "source": [
    "#selezionare un intervallo di tempo (rimuovere alcuni righe del dataframe)\n",
    "print (\"Numero misure (iniziali): \",len(df))\n",
-    "df_new = df.drop(df[df.t <2 ].index | df[df.t > 5].index)\n",
+    "index_to_be_drop = df[ (df.t<2) | (df.t>5) ].index \n",
+    "#df_new = df.drop(df[df.t <2 ].index | df[df.t > 5].index) #obsolete (and not working in some cases)\n",
+    "df_new = df.drop(index_to_be_drop)\n",
    "print (\"Numero misure (dopo i tagli): \",len(df_new))\n",
    "df_new"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 7,
   "id": "767eb950",
   "metadata": {},
   "outputs": [
@@ -764,7 +758,7 @@
       "<AxesSubplot:xlabel='t'>"
      ]
     },
-     "execution_count": 56,
+     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
@@ -788,7 +782,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 8,
   "id": "915d60b5",
   "metadata": {},
   "outputs": [
@@ -815,7 +809,7 @@
       "        0.008447, 0.008671, 0.008896, 0.009124, 0.009354, 0.009586]))"
      ]
     },
-     "execution_count": 57,
+     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -831,17 +825,17 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 9,
   "id": "5d3d8d6a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
-       "[<matplotlib.lines.Line2D at 0x165d00fd0>]"
+       "[<matplotlib.lines.Line2D at 0x164520ee0>]"
      ]
     },
-     "execution_count": 58,
+     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
@@ -862,6 +856,14 @@
    "# grafico a partire dai numpy arrays\n",
    "plt.plot(t,DeltaT,linestyle=\"None\",marker=\".\")"
   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e217e3b2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
  }
 ],
 "metadata": {

 %% Cell type:markdown id:be9885c3 tags:

 Esempio di lettura di un file di test dell'esperimento "Carrello". Il numero di cifre significative nei dati sono arbitrarie. Lo scopo è solo di illustrare alcune funzioni utili di python per lavorare i dati.

 %% Cell type:code id:7d6638fa tags:

 ``` python
 #plots will be shown inline
 %matplotlib inline

 import numpy as np

 import matplotlib.pyplot as plt
 import matplotlib.mlab as mlab

 from scipy import stats

 import pandas as pd
 ```

 %% Cell type:code id:28e10b83 tags:

 ``` python
 # sostituire la virgola con il punto
 reading_file = open("dati_carrello.txt", "r")

 new_file_content = ""
 for line in reading_file:
    stripped_line = line.strip()
    new_line = stripped_line.replace(",", ".")
    new_file_content += new_line +"\n"
 reading_file.close()

 writing_file = open("dati_carrello.txt", "w")
 writing_file.write(new_file_content)
 writing_file.close()
 ```

 %% Cell type:code id:913eb5c9 tags:

 ``` python
 df = pd.read_csv('dati_carrello.txt',header=1,sep='\t') #il separatore in questo caso era un "tab" (\t)
 df
 ```

 %% Output

         Tempo ( s )  Tempo trascorso ( s )
    0         0.0508               0.000685
    1         0.1009               0.000688
    2         0.1510               0.000685
    3         0.2011               0.000685
    4         0.2512               0.000685
    ..           ...                    ...
    114       5.7723               0.010810
    115       5.8222               0.010661
    116       5.8722               0.010560
    117       5.9222               0.010463
    118       5.9722               0.010342
    
    [119 rows x 2 columns]

 %% Cell type:code id:f5f6e2b1 tags:

 ``` python
 #rinominare le colonne
 df = df.rename(columns={"Tempo ( s )": "t", "Tempo trascorso ( s )": "DeltaT"})
 df
 ```

 %% Output

              t    DeltaT
    0    0.0508  0.000685
    1    0.1009  0.000688
    2    0.1510  0.000685
    3    0.2011  0.000685
    4    0.2512  0.000685
    ..      ...       ...
    114  5.7723  0.010810
    115  5.8222  0.010661
    116  5.8722  0.010560
    117  5.9222  0.010463
    118  5.9722  0.010342
    
    [119 rows x 2 columns]

 %% Cell type:code id:033725f4 tags:

 ``` python
 # fare un grafico direttamente dal dataframe
 df.plot(x="t",y="DeltaT",linestyle="None",marker=".")
 ```

 %% Output

    <AxesSubplot:xlabel='t'>



 %% Cell type:code id:36271ccd tags:

 ``` python
 #selezionare un intervallo di tempo (rimuovere alcuni righe del dataframe)
 print ("Numero misure (iniziali): ",len(df))
-df_new = df.drop(df[df.t <2 ].index | df[df.t > 5].index)
+index_to_be_drop = df[ (df.t<2) | (df.t>5) ].index
+#df_new = df.drop(df[df.t <2 ].index | df[df.t > 5].index) #obsolete (and not working in some cases)
+df_new = df.drop(index_to_be_drop)
 print ("Numero misure (dopo i tagli): ",len(df_new))
 df_new
 ```

 %% Output

    Numero misure (iniziali):  119
    Numero misure (dopo i tagli):  60

-    /var/folders/ws/ytnwy3cs0hz8z73rvtwydngm0000gn/T/ipykernel_40871/1233098160.py:3: FutureWarning: Index.__or__ operating as a set operation is deprecated, in the future this will be a logical operation matching Series.__or__.  Use index.union(other) instead
-      df_new = df.drop(df[df.t <2 ].index | df[df.t > 5].index)
-
             t    DeltaT
    39  2.0047  0.000685
    40  2.0548  0.000725
    41  2.1050  0.000793
    42  2.1551  0.000875
    43  2.2053  0.000947
    44  2.2555  0.001020
    45  2.3057  0.001095
    46  2.3558  0.001176
    47  2.4060  0.001252
    48  2.4562  0.001332
    49  2.5064  0.001421
    50  2.5566  0.001512
    51  2.6068  0.001608
    52  2.6570  0.001709
    53  2.7072  0.001811
    54  2.7574  0.001917
    55  2.8076  0.002026
    56  2.8578  0.002138
    57  2.9080  0.002254
    58  2.9582  0.002372
    59  3.0085  0.002494
    60  3.0587  0.002619
    61  3.1089  0.002749
    62  3.1591  0.002880
    63  3.2094  0.003017
    64  3.2596  0.003156
    65  3.3099  0.003298
    66  3.3601  0.003443
    67  3.4104  0.003591
    68  3.4606  0.003741
    69  3.5109  0.003895
    70  3.5611  0.004052
    71  3.6114  0.004211
    72  3.6616  0.004374
    73  3.7119  0.004541
    74  3.7622  0.004709
    75  3.8124  0.004880
    76  3.8627  0.005054
    77  3.9130  0.005232
    78  3.9633  0.005411
    79  4.0136  0.005595
    80  4.0639  0.005782
    81  4.1141  0.005971
    82  4.1644  0.006162
    83  4.2147  0.006357
    84  4.2650  0.006555
    85  4.3153  0.006755
    86  4.3656  0.006958
    87  4.4159  0.007162
    88  4.4662  0.007371
    89  4.5165  0.007580
    90  4.5669  0.007794
    91  4.6172  0.008008
    92  4.6675  0.008227
    93  4.7178  0.008447
    94  4.7681  0.008671
    95  4.8185  0.008896
    96  4.8688  0.009124
    97  4.9191  0.009354
    98  4.9695  0.009586

 %% Cell type:code id:767eb950 tags:

 ``` python
 # grafico nuovo dopo la rimozione delle righe
 df_new.plot(x="t",y="DeltaT",linestyle="None",marker=".")
 ```

 %% Output

    <AxesSubplot:xlabel='t'>



 %% Cell type:code id:915d60b5 tags:

 ``` python
 # se volete, e' possibile trasmormare le colonne del dataframe in numpy arrays.
 t = df_new.t.to_numpy()
 #analogamente
 #t = df_new["t"].to_numpy()
 DeltaT = df_new.DeltaT.to_numpy()
 t,DeltaT
 ```

 %% Output

    (array([2.0047, 2.0548, 2.105 , 2.1551, 2.2053, 2.2555, 2.3057, 2.3558,
            2.406 , 2.4562, 2.5064, 2.5566, 2.6068, 2.657 , 2.7072, 2.7574,
            2.8076, 2.8578, 2.908 , 2.9582, 3.0085, 3.0587, 3.1089, 3.1591,
            3.2094, 3.2596, 3.3099, 3.3601, 3.4104, 3.4606, 3.5109, 3.5611,
            3.6114, 3.6616, 3.7119, 3.7622, 3.8124, 3.8627, 3.913 , 3.9633,
            4.0136, 4.0639, 4.1141, 4.1644, 4.2147, 4.265 , 4.3153, 4.3656,
            4.4159, 4.4662, 4.5165, 4.5669, 4.6172, 4.6675, 4.7178, 4.7681,
            4.8185, 4.8688, 4.9191, 4.9695]),
     array([0.000685, 0.000725, 0.000793, 0.000875, 0.000947, 0.00102 ,
            0.001095, 0.001176, 0.001252, 0.001332, 0.001421, 0.001512,
            0.001608, 0.001709, 0.001811, 0.001917, 0.002026, 0.002138,
            0.002254, 0.002372, 0.002494, 0.002619, 0.002749, 0.00288 ,
            0.003017, 0.003156, 0.003298, 0.003443, 0.003591, 0.003741,
            0.003895, 0.004052, 0.004211, 0.004374, 0.004541, 0.004709,
            0.00488 , 0.005054, 0.005232, 0.005411, 0.005595, 0.005782,
            0.005971, 0.006162, 0.006357, 0.006555, 0.006755, 0.006958,
            0.007162, 0.007371, 0.00758 , 0.007794, 0.008008, 0.008227,
            0.008447, 0.008671, 0.008896, 0.009124, 0.009354, 0.009586]))

 %% Cell type:code id:5d3d8d6a tags:

 ``` python
 # grafico a partire dai numpy arrays
 plt.plot(t,DeltaT,linestyle="None",marker=".")
 ```

 %% Output

-    [<matplotlib.lines.Line2D at 0x165d00fd0>]
+    [<matplotlib.lines.Line2D at 0x164520ee0>]


+
+%% Cell type:code id:e217e3b2 tags:
+
+``` python
+```