"C:\\Users\\Joaquín Torres\\AppData\\Local\\Temp\\ipykernel_8220\\1003504044.py:14: FutureWarning: The behavior of Series.replace (and DataFrame.replace) with CategoricalDtype is deprecated. In a future version, replace will only be used for cases that preserve the categories. To change the categories, use ser.cat.rename_categories instead.\n",
"C:\\Users\\Joaquín Torres\\AppData\\Local\\Temp\\ipykernel_8220\\3303146707.py:2: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
"The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
"\n",
"For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
"\n",
"\n",
" bd['Age'].fillna(age_mode, inplace=True)\n",
"C:\\Users\\Joaquín Torres\\AppData\\Local\\Temp\\ipykernel_8220\\3303146707.py:5: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
"The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
"\n",
"For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
"C:\\Users\\Joaquín Torres\\AppData\\Local\\Temp\\ipykernel_8220\\3303146707.py:8: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
"The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
"\n",
"For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
"C:\\Users\\Joaquín Torres\\AppData\\Local\\Temp\\ipykernel_8220\\3303146707.py:11: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
"The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
"\n",
"For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
" # If not, use redefined version through mapping\n",
" else:\n",
" ind_vars_enc.append(ind_var + '_REDEF')\n",
"\n",
"# Final version of columns we need to use for correlation analysis\n",
"corr_cols = soc_vars_enc + ind_vars_enc"
]
},
{
"cell_type": "code",
"execution_count": 81,
"metadata": {},
"outputs": [],
"source": [
"# Drop unknown columns\n",
"corr_cols = [corr_col for corr_col in corr_cols if corr_col not in ['Ed_Unknowledge', 'JobIn_unkwnodledge', 'Hous_unknowledge', 'Frec30_Desconocido']]\n",
"soc_vars_enc = [corr_col for corr_col in soc_vars_enc if corr_col not in ['Ed_Unknowledge', 'JobIn_unkwnodledge', 'Hous_unknowledge', 'Frec30_Desconocido']]\n",
"ind_vars_enc = [corr_col for corr_col in soc_vars_enc if ind_vars_enc not in ['Ed_Unknowledge', 'JobIn_unkwnodledge', 'Hous_unknowledge', 'Frec30_Desconocido']]"
"binary_vars = [col for col in corr_cols if len(bd[col].unique()) == 2] + [name_mapping['Situacion_tratamiento_REDEF'], name_mapping['Risk_stigma_REDEF']]\n",
"cont_vars = [name_mapping[col] for col in ['Structural_conflic', 'Age', 'NumHijos', 'Años_consumo_droga', 'Adherencia_tto_recalc']]"
]
},
{
"cell_type": "code",
"execution_count": 90,
"metadata": {},
"outputs": [],
"source": [
"def get_corr_matrix(df, cols):\n",
" \n",
" # Initialize nxn matrix to zeroes\n",
" n = len(cols)\n",
" corr_matrix = np.zeros((n,n))\n",
"\n",
" for i, var_i in enumerate(cols):\n",
" for j, var_j in enumerate(cols):\n",
" # Fill lower triangle of matrix\n",
" if i > j:\n",
" # Binary with binary correlation: tetrachoric\n",
" if var_i in binary_vars and var_j in binary_vars:\n",
