File size: 5,835 Bytes
5ad4396
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
{
  "cells": [
    {
      "cell_type": "markdown",
      "id": "eaa22304",
      "metadata": {
        "id": "eaa22304"
      },
      "source": [
        "### Kernel Density Estimation  \n",
        "Given n data points, X$\\in R^{n\\times m}$, estimate the probability density function of the data i.e. Prob(x).\n",
        "\n",
        "In KDE, the pdf is given by $P(x) = \\frac{1}{nh}\\sum_{i=1}^{N}K(\\frac{X_i-x}{h})$,\n",
        "where K is the kernel function, h is smoothing bandwidth (small h undersmoothing, large h oversmoothing)."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "e139aff4",
      "metadata": {
        "id": "e139aff4"
      },
      "outputs": [],
      "source": [
        "import sklearn\n",
        "import fnmatch\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import seaborn as sns\n",
        "import statsmodels.api as sm\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.decomposition import PCA\n",
        "from sklearn.neighbors import KernelDensity\n",
        "from sklearn.model_selection import GridSearchCV"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "14a48fb0",
      "metadata": {
        "id": "14a48fb0"
      },
      "source": [
        "#### Load the real data and select samples for a specific race and sex"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "c784a28b",
      "metadata": {
        "id": "c784a28b"
      },
      "outputs": [],
      "source": [
        "df = pd.read_csv('istaging_all.csv') # load istaging data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "0159223c",
      "metadata": {
        "id": "0159223c"
      },
      "outputs": [],
      "source": [
        "# select black females\n",
        "df = df[((df.Race == 'Black') & (df.Sex == 'F'))].reset_index(drop=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "0758d447",
      "metadata": {
        "id": "0758d447"
      },
      "outputs": [],
      "source": [
        "# select baseline data for each subject\n",
        "df.Date = pd.to_datetime(df.Date)\n",
        "df_tp1 = df.loc[df.groupby('PTID')['Date'].idxmin()].reset_index(drop=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "9611e735",
      "metadata": {
        "scrolled": true,
        "id": "9611e735"
      },
      "outputs": [],
      "source": [
        "# split the data to train and test set, train set will be used to learn the probablity distribtuion of the real data\n",
        "df_train, df_test = sklearn.model_selection.train_test_split(df_tp1, test_size=0.3, random_state=40)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "0800ceda",
      "metadata": {
        "id": "0800ceda"
      },
      "source": [
        "#### Fit a KDE model to estimate the joint probability density of Age and ROI volumes."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "b37250f8",
      "metadata": {
        "id": "b37250f8"
      },
      "outputs": [],
      "source": [
        "## standardized ROI grid search\n",
        "# use grid search to select the bandwidth\n",
        "cols = ['Age']\n",
        "roi_cols = [] #fill in with the roi column names\n",
        "cols.extend(fnmatch.filter(df_train.columns, roi_cols)) # select the ROI volumes\n",
        "data = df_train.loc[:, cols].to_numpy()\n",
        "data_standard = pd.DataFrame()\n",
        "# standardize the data\n",
        "data_standard['Age'] = (df_train['Age'] - df_train.loc[:, 'Age'].mean()) / df_train.loc[:, 'Age'].std()\n",
        "data_standard[cols[1:]] =  ((df_train.loc[:, cols[1:]] - df_train.loc[:, cols[1:]].mean()) / df_train.loc[:, cols[1:]].std())\n",
        "data_standard = data_standard.to_numpy()\n",
        "\n",
        "# Use a Gaussian kernel\n",
        "kde = GridSearchCV(KernelDensity(kernel='gaussian'),{'bandwidth': np.linspace(0, 3, 100)}, cv=5)\n",
        "kde.fit(data_standard)\n",
        "kde = kde.best_estimator_\n",
        "print(f'optimal bandwidth of kernel estimated via grid search is {kde.bandwidth_} ')"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "32c78445",
      "metadata": {
        "id": "32c78445"
      },
      "source": [
        "#### Generate synthetic data using a KDE model for the specified category of race and sex"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "e06523c2",
      "metadata": {
        "id": "e06523c2"
      },
      "outputs": [],
      "source": [
        "# sample 3000 data points\n",
        "sample = kde.sample(3000, random_state=0)\n",
        "sample[:, :] = np.multiply(sample[:, :], df_train.loc[:, cols[:]].std().tolist()) + df_train.loc[:, cols[:]].mean().tolist()\n",
        "cov_list = np.array([[f'Synth_{i+1}', 'F', 'Black'] for i in range(3000)])\n",
        "synthetic_data = np.concatenate([cov_list, sample], axis=1)\n",
        "cols=['PTID', 'Sex', 'Race', 'Age']\n",
        "cols.extend(roi_cols)\n",
        "df_kde_synth = pd.DataFrame(synthetic_data, columns=cols)"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.8.8"
    },
    "colab": {
      "provenance": []
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}