fix problem with drop

ac86373a · Francesco Santanastasio · 4951f96e · ac86373a
Commit ac86373a authored 10 months ago by Francesco Santanastasio
--- a/TestVolano.ipynb
+++ b/TestVolano.ipynb
@@ -683,7 +683,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
   "id": "d97129d6",
   "metadata": {},
   "outputs": [
@@ -695,14 +695,6 @@
      "Numero misure (dopo i tagli):  3001\n"
     ]
    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/var/folders/ws/ytnwy3cs0hz8z73rvtwydngm0000gn/T/ipykernel_3699/2728226843.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 <20 ].index | df[df.t > 80].index)\n"
-     ]
-    },
    {
     "data": {
      "text/html": [
@@ -866,7 +858,7 @@
       "[3001 rows x 7 columns]"
      ]
     },
-     "execution_count": 7,
+     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -874,7 +866,9 @@
   "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 <20 ].index | df[df.t > 80].index)\n",
+    "index_to_be_drop = df[ (df.t<20) | (df.t>80) ].index \n",
+    "#df_new = df.drop(df[df.t <20 ].index | df[df.t > 80].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:markdown id:a668e702 tags:

 Esempio di lettura di un file di test dell'esperimento "Volano". 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:2c3314df 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:1313521e tags:

 ``` python
 # sostituire la virgola con il punto
 reading_file = open("dati_volano_raw.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_volano.txt", "w")
 writing_file.write(new_file_content)
 writing_file.close()
 ```

 %% Cell type:code id:7d55cb2e tags:

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

 %% Output

          Time (s)  Angle (rad)  Angular Velocity (rad/s)  \
    0         0.02     0.000000                       NaN
    1         0.04     0.000000                   0.00000
    2         0.06     0.000000                   0.00000
    3         0.08     0.000000                   0.00000
    4         0.10     0.000000                   0.00000
    ...        ...          ...                       ...
    4805     96.12    -9.501754                  -0.03927
    4806     96.14    -9.501754                   0.00000
    4807     96.16    -9.501754                   0.00000
    4808     96.18    -9.501754                   0.00000
    4809     96.20    -9.501754                   0.00000
    
          Angular Acceleration (rad/s²)  Position (m)  Velocity (m/s)  \
    0                               NaN      0.000000             NaN
    1                               NaN      0.000000        0.000000
    2                          0.000000      0.000000        0.000000
    3                          0.000000      0.000000        0.000000
    4                          0.000000      0.000000        0.000000
    ...                             ...           ...             ...
    4805                       0.981748     -0.226837       -0.000937
    4806                       0.981748     -0.226837        0.000000
    4807                       0.000000     -0.226837        0.000000
    4808                       0.000000     -0.226837        0.000000
    4809                            NaN     -0.226837        0.000000
    
          Acceleration (m/s²)
    0                     NaN
    1                     NaN
    2                0.000000
    3                0.000000
    4                0.000000
    ...                   ...
    4805             0.023438
    4806             0.023438
    4807             0.000000
    4808             0.000000
    4809                  NaN
    
    [4810 rows x 7 columns]

 %% Cell type:code id:7eb3c699 tags:

 ``` python
 # remove lines with "NaN" (Not a Number)
 df = df.dropna()
 df
 ```

 %% Output

          Time (s)  Angle (rad)  Angular Velocity (rad/s)  \
    2         0.06     0.000000                   0.00000
    3         0.08     0.000000                   0.00000
    4         0.10     0.000000                   0.00000
    5         0.12     0.000000                   0.00000
    6         0.14     0.000000                   0.00000
    ...        ...          ...                       ...
    4804     96.10    -9.500183                  -0.03927
    4805     96.12    -9.501754                  -0.03927
    4806     96.14    -9.501754                   0.00000
    4807     96.16    -9.501754                   0.00000
    4808     96.18    -9.501754                   0.00000
    
          Angular Acceleration (rad/s²)  Position (m)  Velocity (m/s)  \
    2                          0.000000      0.000000        0.000000
    3                          0.000000      0.000000        0.000000
    4                          0.000000      0.000000        0.000000
    5                          0.000000      0.000000        0.000000
    6                          0.000000      0.000000        0.000000
    ...                             ...           ...             ...
    4804                      -0.981748     -0.226800       -0.000937
    4805                       0.981748     -0.226837       -0.000937
    4806                       0.981748     -0.226837        0.000000
    4807                       0.000000     -0.226837        0.000000
    4808                       0.000000     -0.226837        0.000000
    
          Acceleration (m/s²)
    2                0.000000
    3                0.000000
    4                0.000000
    5                0.000000
    6                0.000000
    ...                   ...
    4804            -0.023438
    4805             0.023438
    4806             0.023438
    4807             0.000000
    4808             0.000000
    
    [4807 rows x 7 columns]

 %% Cell type:code id:c9e70ccf tags:

 ``` python
 #rinominare le colonne
 df = df.rename(columns={"Time (s)": "t"
                        , "Angle (rad)": "angle"
                        , "Angular Velocity (rad/s)": "angle_v"
                        , "Angular Acceleration (rad/s²)": "angle_a"
                        , "Position (m)": "x"
                        , "Velocity (m/s)": "v"
                        , "Acceleration (m/s²)": "a"} )
 df
 ```

 %% Output

              t     angle  angle_v   angle_a         x         v         a
    2      0.06  0.000000  0.00000  0.000000  0.000000  0.000000  0.000000
    3      0.08  0.000000  0.00000  0.000000  0.000000  0.000000  0.000000
    4      0.10  0.000000  0.00000  0.000000  0.000000  0.000000  0.000000
    5      0.12  0.000000  0.00000  0.000000  0.000000  0.000000  0.000000
    6      0.14  0.000000  0.00000  0.000000  0.000000  0.000000  0.000000
    ...     ...       ...      ...       ...       ...       ...       ...
    4804  96.10 -9.500183 -0.03927 -0.981748 -0.226800 -0.000937 -0.023438
    4805  96.12 -9.501754 -0.03927  0.981748 -0.226837 -0.000937  0.023438
    4806  96.14 -9.501754  0.00000  0.981748 -0.226837  0.000000  0.023438
    4807  96.16 -9.501754  0.00000  0.000000 -0.226837  0.000000  0.000000
    4808  96.18 -9.501754  0.00000  0.000000 -0.226837  0.000000  0.000000
    
    [4807 rows x 7 columns]

 %% Cell type:code id:3982ec4f tags:

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

 %% Output

    <AxesSubplot:xlabel='t'>



 %% Cell type:code id:d97129d6 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 <20 ].index | df[df.t > 80].index)
+index_to_be_drop = df[ (df.t<20) | (df.t>80) ].index
+#df_new = df.drop(df[df.t <20 ].index | df[df.t > 80].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):  4807
    Numero misure (dopo i tagli):  3001

-    /var/folders/ws/ytnwy3cs0hz8z73rvtwydngm0000gn/T/ipykernel_3699/2728226843.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 <20 ].index | df[df.t > 80].index)
-
              t     angle  angle_v       angle_a         x         v             a
    999   20.00 -1.072855  0.00000  0.000000e+00 -0.025612  0.000000  0.000000e+00
    1000  20.02 -1.072855  0.00000  0.000000e+00 -0.025612  0.000000  0.000000e+00
    1001  20.04 -1.072855  0.00000  9.817484e-01 -0.025612  0.000000  2.343750e-02
    1002  20.06 -1.072855  0.03927  9.817484e-01 -0.025612  0.000937  2.343750e-02
    1003  20.08 -1.071284  0.03927 -9.817484e-01 -0.025575  0.000937 -2.343750e-02
    ...     ...       ...      ...           ...       ...       ...           ...
    3995  79.92 -8.089607 -0.03927  0.000000e+00 -0.193125 -0.000937  0.000000e+00
    3996  79.94 -8.091178  0.00000  1.963497e+00 -0.193162  0.000000  4.687500e-02
    3997  79.96 -8.089607  0.03927  9.817484e-01 -0.193125  0.000937  2.343750e-02
    3998  79.98 -8.089607  0.03927  3.488529e-13 -0.193125  0.000937  8.326673e-15
    3999  80.00 -8.088036  0.03927 -9.817484e-01 -0.193087  0.000937 -2.343750e-02
    
    [3001 rows x 7 columns]

 %% Cell type:code id:9a93e1ad tags:

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

 %% Output

    <AxesSubplot:xlabel='t'>



 %% Cell type:code id:11174ec4 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()
 x = df_new.x.to_numpy()
 t,x
 ```

 %% Output

    (array([20.  , 20.02, 20.04, ..., 79.96, 79.98, 80.  ]),
     array([-0.0256125, -0.0256125, -0.0256125, ..., -0.193125 , -0.193125 ,
            -0.1930875]))

 %% Cell type:code id:03d36daa tags:

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

 %% Output

    [<matplotlib.lines.Line2D at 0x15a5f89a0>]



 %% Cell type:code id:7d1e0701 tags:

 ``` python
 ```