Save labels as str

577832a7 · Alessia Marcolini · 0cc3ac68 · 577832a7
Commit 577832a7 authored Oct 16, 2019 by Alessia Marcolini
--- a/preprocessing/group_T-stage.ipynb
+++ b/preprocessing/group_T-stage.ipynb
@@ -298,24 +298,24 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "grading_dict = {\n",
-    "    'T1': 0,\n",
-    "    'T2': 0,\n",
-    "    'T3': 1,\n",
-    "    'T4': 1,\n",
-    "    'T4a': 1,\n",
-    "    'T4b': 1,\n",
-    "    'Tx': 1,\n",
+    "    'T1': '0',\n",
+    "    'T2': '0',\n",
+    "    'T3': '1',\n",
+    "    'T4': '1',\n",
+    "    'T4a': '1',\n",
+    "    'T4b': '1',\n",
+    "    'Tx': '1',\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [

 %% Cell type:code id: tags:

 ``` python
 %HN_env
 ```

 %% Output

    <IPython.core.display.HTML object>

 %% Cell type:code id: tags:

 ``` python
 import os
 # base path of the project
 PATH = os.path.join(os.path.abspath(os.path.curdir), '..')
 ```

 %% Cell type:code id: tags:

 ``` python
 import numpy as np
 import pandas as pd
 ```

 %% Cell type:code id: tags:

 ``` python
 clinical = pd.read_csv(f'{PATH}/data/clinical_data.csv')
 ```

 %% Cell type:code id: tags:

 ``` python
 clinical.head()
 ```

 %% Output

        Patient # Sex   Age Primary Site T-stage N-stage M-stage TNM group stage  \
    0  HN-HGJ-001   M  79.0       Larynx      T3      N0      M0       stage III
    1  HN-HGJ-002   M  41.0  Nasopharynx      T1      N1      M0       stage IIB
    2  HN-HGJ-003   M  75.0       Larynx      T3     N2b      M0       stage IVA
    3  HN-HGJ-004   M  53.0  Nasopharynx      T3      N1      M0       stage III
    4  HN-HGJ-005   M  74.0  Nasopharynx      T1      N1      M0       stage IIB
    
      HPV status  Time – diagnosis to diagnosis (days)  ...  Surgery  \
    0          -                                     0  ...      0.0
    1          -                                     0  ...      0.0
    2        NaN                                     0  ...      0.0
    3        NaN                                     0  ...      0.0
    4          -                                     0  ...      0.0
    
      Time – diagnosis to last follow-up(days)  Locoregional  Distant Death  \
    0                                     2123             1        0     0
    1                                     2114             1        0     0
    2                                     1098             1        1     1
    3                                     2974             0        0     0
    4                                     2509             0        0     1
    
       Time – diagnosis to LR (days)  Time – diagnosis to DM (days)  \
    0                          692.0                            NaN
    1                          918.0                            NaN
    2                          441.0                          441.0
    3                            NaN                            NaN
    4                            NaN                            NaN
    
       Time – diagnosis to Death (days)  stage  stage_simple
    0                               NaN    III           III
    1                               NaN    IIB            II
    2                            1098.0    IVA            IV
    3                               NaN    III           III
    4                            2509.0    IIB            II
    
    [5 rows x 25 columns]

 %% Cell type:code id: tags:

 ``` python
 pd.unique(clinical['T-stage'].values)
 ```

 %% Output

    array(['T3', 'T1', 'T4', 'T2', 'Tx', 'T4b', 'T4a'], dtype=object)

 %% Cell type:code id: tags:

 ``` python
 grading_dict = {
-    'T1': 0,
-    'T2': 0,
-    'T3': 1,
-    'T4': 1,
-    'T4a': 1,
-    'T4b': 1,
-    'Tx': 1,
+    'T1': '0',
+    'T2': '0',
+    'T3': '1',
+    'T4': '1',
+    'T4a': '1',
+    'T4b': '1',
+    'Tx': '1',
 }
 ```

 %% Cell type:code id: tags:

 ``` python
 clinical['T-stage_grouped'] = clinical['T-stage'].apply(lambda x: grading_dict[x])
 ```

 %% Cell type:code id: tags:

 ``` python
 clinical.head()
 ```

 %% Output

        Patient # Sex   Age Primary Site T-stage N-stage M-stage TNM group stage  \
    0  HN-HGJ-001   M  79.0       Larynx      T3      N0      M0       stage III
    1  HN-HGJ-002   M  41.0  Nasopharynx      T1      N1      M0       stage IIB
    2  HN-HGJ-003   M  75.0       Larynx      T3     N2b      M0       stage IVA
    3  HN-HGJ-004   M  53.0  Nasopharynx      T3      N1      M0       stage III
    4  HN-HGJ-005   M  74.0  Nasopharynx      T1      N1      M0       stage IIB
    
      HPV status  Time – diagnosis to diagnosis (days)  ...  \
    0          -                                     0  ...
    1          -                                     0  ...
    2        NaN                                     0  ...
    3        NaN                                     0  ...
    4          -                                     0  ...
    
       Time – diagnosis to last follow-up(days) Locoregional  Distant  Death  \
    0                                      2123            1        0      0
    1                                      2114            1        0      0
    2                                      1098            1        1      1
    3                                      2974            0        0      0
    4                                      2509            0        0      1
    
      Time – diagnosis to LR (days)  Time – diagnosis to DM (days)  \
    0                         692.0                            NaN
    1                         918.0                            NaN
    2                         441.0                          441.0
    3                           NaN                            NaN
    4                           NaN                            NaN
    
       Time – diagnosis to Death (days)  stage  stage_simple  T-stage_grouped
    0                               NaN    III           III                1
    1                               NaN    IIB            II                0
    2                            1098.0    IVA            IV                1
    3                               NaN    III           III                1
    4                            2509.0    IIB            II                0
    
    [5 rows x 26 columns]

 %% Cell type:code id: tags:

 ``` python
 clinical.to_csv(f'{PATH}/data/clinical_data.csv', index=False)
 ```

 %% Cell type:code id: tags:

 ``` python
 ```