v.vichi3
/
Neural_Network_for_MOID_Prediction
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
main
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '35a0e891fd'
${ noResults }
Neural_Network_for_MOID_Pre.../neos_dataset_preprocessing....

1045 lines
774 KiB
Plaintext
Raw Normal View History Unescape Escape

Jupyter Notebook for pre-processing of the NEOs DataFrame
7 months ago
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "b97688d5-dbd8-451e-924b-902649ef3712",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"import math"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "838b4878-cb24-4330-ac58-48de11ee1372",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>spkid</th>\n",
" <th>pha</th>\n",
" <th>H</th>\n",
" <th>epoch_mjd</th>\n",
" <th>e</th>\n",
" <th>a</th>\n",
" <th>i</th>\n",
" <th>om</th>\n",
" <th>w</th>\n",
" <th>ma</th>\n",
" <th>moid</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>20000433</td>\n",
" <td>N</td>\n",
" <td>10.41</td>\n",
" <td>60400</td>\n",
" <td>0.2227</td>\n",
" <td>1.458</td>\n",
" <td>10.83</td>\n",
" <td>304.28</td>\n",
" <td>178.90</td>\n",
" <td>334.73</td>\n",
" <td>0.1500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>20000719</td>\n",
" <td>N</td>\n",
" <td>15.59</td>\n",
" <td>60400</td>\n",
" <td>0.5469</td>\n",
" <td>2.636</td>\n",
" <td>11.58</td>\n",
" <td>183.85</td>\n",
" <td>156.22</td>\n",
" <td>102.37</td>\n",
" <td>0.2010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>20000887</td>\n",
" <td>N</td>\n",
" <td>13.88</td>\n",
" <td>60400</td>\n",
" <td>0.5710</td>\n",
" <td>2.472</td>\n",
" <td>9.40</td>\n",
" <td>110.42</td>\n",
" <td>350.48</td>\n",
" <td>289.48</td>\n",
" <td>0.0803</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>20001036</td>\n",
" <td>N</td>\n",
" <td>9.26</td>\n",
" <td>60400</td>\n",
" <td>0.5328</td>\n",
" <td>2.665</td>\n",
" <td>26.69</td>\n",
" <td>215.50</td>\n",
" <td>132.48</td>\n",
" <td>321.69</td>\n",
" <td>0.3450</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20001221</td>\n",
" <td>N</td>\n",
" <td>17.38</td>\n",
" <td>60400</td>\n",
" <td>0.4352</td>\n",
" <td>1.920</td>\n",
" <td>11.88</td>\n",
" <td>171.31</td>\n",
" <td>26.68</td>\n",
" <td>197.64</td>\n",
" <td>0.1080</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" spkid pha H epoch_mjd e a i om w \\\n",
"0 20000433 N 10.41 60400 0.2227 1.458 10.83 304.28 178.90 \n",
"1 20000719 N 15.59 60400 0.5469 2.636 11.58 183.85 156.22 \n",
"2 20000887 N 13.88 60400 0.5710 2.472 9.40 110.42 350.48 \n",
"3 20001036 N 9.26 60400 0.5328 2.665 26.69 215.50 132.48 \n",
"4 20001221 N 17.38 60400 0.4352 1.920 11.88 171.31 26.68 \n",
"\n",
" ma moid \n",
"0 334.73 0.1500 \n",
"1 102.37 0.2010 \n",
"2 289.48 0.0803 \n",
"3 321.69 0.3450 \n",
"4 197.64 0.1080 "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"folder='/home/unipi/v.vichi3/Desktop/'\n",
"df=pd.read_csv(folder+'sbdb_query_results.csv')\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "7f165f80-3253-49b0-b43c-a8722f60e57b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(34901, 11)"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "c41deece-a459-4ef3-8c83-0f87756dac92",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['spkid', 'pha', 'H', 'epoch_mjd', 'e', 'a', 'i', 'om', 'w', 'ma',\n",
" 'moid'],\n",
" dtype='object')"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "f91e7f7c-4d5a-44c8-b0ba-9c2b71a01839",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 34901 entries, 0 to 34900\n",
"Data columns (total 11 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 spkid 34901 non-null int64 \n",
" 1 pha 34875 non-null object \n",
" 2 H 34897 non-null float64\n",
" 3 epoch_mjd 34901 non-null int64 \n",
" 4 e 34901 non-null float64\n",
" 5 a 34901 non-null float64\n",
" 6 i 34901 non-null float64\n",
" 7 om 34901 non-null float64\n",
" 8 w 34901 non-null float64\n",
" 9 ma 34901 non-null float64\n",
" 10 moid 34876 non-null float64\n",
"dtypes: float64(8), int64(2), object(1)\n",
"memory usage: 2.9+ MB\n"
]
}
],
"source": [
"df.info()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "eb543294-e46b-431e-862a-a0244cadd9fc",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(34876, 11)"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Eliminate the null values\n",
"df.drop(df[df['moid'].isna()].index,inplace=True)\n",
"df.reset_index(drop=True,inplace=True)\n",
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "e4ad2c21-bd10-4714-9d9a-aeb4ed639b36",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>spkid</th>\n",
" <th>H</th>\n",
" <th>epoch_mjd</th>\n",
" <th>e</th>\n",
" <th>a</th>\n",
" <th>i</th>\n",
" <th>om</th>\n",
" <th>w</th>\n",
" <th>ma</th>\n",
" <th>moid</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>3.487600e+04</td>\n",
" <td>34872.000000</td>\n",
" <td>34876.000000</td>\n",
" <td>34876.000000</td>\n",
" <td>34876.000000</td>\n",
" <td>34876.000000</td>\n",
" <td>34876.000000</td>\n",
" <td>34876.000000</td>\n",
" <td>34876.000000</td>\n",
" <td>3.487600e+04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>2.359880e+07</td>\n",
" <td>23.486083</td>\n",
" <td>59701.479986</td>\n",
" <td>0.437249</td>\n",
" <td>1.764192</td>\n",
" <td>12.005071</td>\n",
" <td>171.924096</td>\n",
" <td>182.571561</td>\n",
" <td>171.755088</td>\n",
" <td>8.552434e-02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>2.362820e+07</td>\n",
" <td>2.894608</td>\n",
" <td>1572.136162</td>\n",
" <td>0.176989</td>\n",
" <td>2.117845</td>\n",
" <td>10.694688</td>\n",
" <td>103.659852</td>\n",
" <td>104.303965</td>\n",
" <td>122.272791</td>\n",
" <td>9.834009e-02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>3.001703e+06</td>\n",
" <td>9.260000</td>\n",
" <td>44221.000000</td>\n",
" <td>0.002800</td>\n",
" <td>0.461700</td>\n",
" <td>0.010000</td>\n",
" <td>0.010000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>4.540000e-07</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>3.701855e+06</td>\n",
" <td>21.320000</td>\n",
" <td>59976.000000</td>\n",
" <td>0.304500</td>\n",
" <td>1.294000</td>\n",
" <td>4.420000</td>\n",
" <td>80.380000</td>\n",
" <td>93.357500</td>\n",
" <td>49.480000</td>\n",
" <td>1.280000e-02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>3.843806e+06</td>\n",
" <td>23.800000</td>\n",
" <td>60400.000000</td>\n",
" <td>0.451700</td>\n",
" <td>1.693000</td>\n",
" <td>8.490000</td>\n",
" <td>171.660000</td>\n",
" <td>184.530000</td>\n",
" <td>164.700000</td>\n",
" <td>4.520000e-02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>5.416717e+07</td>\n",
" <td>25.600000</td>\n",
" <td>60400.000000</td>\n",
" <td>0.565000</td>\n",
" <td>2.172000</td>\n",
" <td>16.810000</td>\n",
" <td>252.402500</td>\n",
" <td>272.662500</td>\n",
" <td>291.902500</td>\n",
" <td>1.280000e-01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>5.443990e+07</td>\n",
" <td>33.580000</td>\n",
" <td>60435.000000</td>\n",
" <td>0.996200</td>\n",
" <td>332.600000</td>\n",
" <td>165.580000</td>\n",
" <td>359.980000</td>\n",
" <td>359.960000</td>\n",
" <td>360.000000</td>\n",
" <td>7.080000e-01</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" spkid H epoch_mjd e a \\\n",
"count 3.487600e+04 34872.000000 34876.000000 34876.000000 34876.000000 \n",
"mean 2.359880e+07 23.486083 59701.479986 0.437249 1.764192 \n",
"std 2.362820e+07 2.894608 1572.136162 0.176989 2.117845 \n",
"min 3.001703e+06 9.260000 44221.000000 0.002800 0.461700 \n",
"25% 3.701855e+06 21.320000 59976.000000 0.304500 1.294000 \n",
"50% 3.843806e+06 23.800000 60400.000000 0.451700 1.693000 \n",
"75% 5.416717e+07 25.600000 60400.000000 0.565000 2.172000 \n",
"max 5.443990e+07 33.580000 60435.000000 0.996200 332.600000 \n",
"\n",
" i om w ma moid \n",
"count 34876.000000 34876.000000 34876.000000 34876.000000 3.487600e+04 \n",
"mean 12.005071 171.924096 182.571561 171.755088 8.552434e-02 \n",
"std 10.694688 103.659852 104.303965 122.272791 9.834009e-02 \n",
"min 0.010000 0.010000 0.000000 0.000000 4.540000e-07 \n",
"25% 4.420000 80.380000 93.357500 49.480000 1.280000e-02 \n",
"50% 8.490000 171.660000 184.530000 164.700000 4.520000e-02 \n",
"75% 16.810000 252.402500 272.662500 291.902500 1.280000e-01 \n",
"max 165.580000 359.980000 359.960000 360.000000 7.080000e-01 "
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.describe()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "292a8389-dcdb-4381-a547-0426c56b8fb0",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>spkid</th>\n",
" <th>pha</th>\n",
" <th>H</th>\n",
" <th>epoch_mjd</th>\n",
" <th>e</th>\n",
" <th>a</th>\n",
" <th>i</th>\n",
" <th>om</th>\n",
" <th>w</th>\n",
" <th>ma</th>\n",
" <th>moid</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>3510</th>\n",
" <td>3024715</td>\n",
" <td>Y</td>\n",
" <td>17.69</td>\n",
" <td>60400</td>\n",
" <td>0.9480</td>\n",
" <td>17.800</td>\n",
" <td>19.67</td>\n",
" <td>48.69</td>\n",
" <td>333.32</td>\n",
" <td>117.04</td>\n",
" <td>0.0111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6483</th>\n",
" <td>3434371</td>\n",
" <td>N</td>\n",
" <td>24.11</td>\n",
" <td>54767</td>\n",
" <td>0.9060</td>\n",
" <td>7.315</td>\n",
" <td>32.39</td>\n",
" <td>213.81</td>\n",
" <td>263.82</td>\n",
" <td>357.31</td>\n",
" <td>0.1090</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11522</th>\n",
" <td>3683246</td>\n",
" <td>N</td>\n",
" <td>20.00</td>\n",
" <td>60400</td>\n",
" <td>0.9407</td>\n",
" <td>21.440</td>\n",
" <td>93.63</td>\n",
" <td>338.57</td>\n",
" <td>311.75</td>\n",
" <td>35.25</td>\n",
" <td>0.4590</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15455</th>\n",
" <td>3766081</td>\n",
" <td>N</td>\n",
" <td>16.27</td>\n",
" <td>57742</td>\n",
" <td>0.9919</td>\n",
" <td>153.200</td>\n",
" <td>145.50</td>\n",
" <td>165.97</td>\n",
" <td>77.94</td>\n",
" <td>360.00</td>\n",
" <td>0.5970</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17114</th>\n",
" <td>3799259</td>\n",
" <td>N</td>\n",
" <td>21.20</td>\n",
" <td>60400</td>\n",
" <td>0.9962</td>\n",
" <td>332.600</td>\n",
" <td>108.34</td>\n",
" <td>219.67</td>\n",
" <td>151.26</td>\n",
" <td>0.39</td>\n",
" <td>0.3330</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19835</th>\n",
" <td>3840692</td>\n",
" <td>N</td>\n",
" <td>22.61</td>\n",
" <td>60400</td>\n",
" <td>0.9889</td>\n",
" <td>96.930</td>\n",
" <td>139.83</td>\n",
" <td>340.62</td>\n",
" <td>193.09</td>\n",
" <td>1.90</td>\n",
" <td>0.1010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20634</th>\n",
" <td>3843547</td>\n",
" <td>N</td>\n",
" <td>18.68</td>\n",
" <td>60400</td>\n",
" <td>0.7984</td>\n",
" <td>5.774</td>\n",
" <td>10.98</td>\n",
" <td>348.98</td>\n",
" <td>57.12</td>\n",
" <td>114.87</td>\n",
" <td>0.2340</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20682</th>\n",
" <td>3843840</td>\n",
" <td>N</td>\n",
" <td>18.17</td>\n",
" <td>58729</td>\n",
" <td>0.9789</td>\n",
" <td>59.680</td>\n",
" <td>159.03</td>\n",
" <td>187.95</td>\n",
" <td>176.27</td>\n",
" <td>0.09</td>\n",
" <td>0.2580</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20698</th>\n",
" <td>3843628</td>\n",
" <td>N</td>\n",
" <td>21.20</td>\n",
" <td>60400</td>\n",
" <td>0.7734</td>\n",
" <td>5.693</td>\n",
" <td>13.57</td>\n",
" <td>252.31</td>\n",
" <td>75.55</td>\n",
" <td>122.88</td>\n",
" <td>0.3770</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20742</th>\n",
" <td>3843716</td>\n",
" <td>N</td>\n",
" <td>20.05</td>\n",
" <td>60400</td>\n",
" <td>0.7984</td>\n",
" <td>5.775</td>\n",
" <td>10.96</td>\n",
" <td>348.94</td>\n",
" <td>57.16</td>\n",
" <td>114.83</td>\n",
" <td>0.2330</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22110</th>\n",
" <td>3989287</td>\n",
" <td>N</td>\n",
" <td>18.12</td>\n",
" <td>60400</td>\n",
" <td>0.9213</td>\n",
" <td>7.701</td>\n",
" <td>165.58</td>\n",
" <td>105.87</td>\n",
" <td>57.80</td>\n",
" <td>66.15</td>\n",
" <td>0.0817</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28090</th>\n",
" <td>54240416</td>\n",
" <td>N</td>\n",
" <td>18.61</td>\n",
" <td>60400</td>\n",
" <td>0.8883</td>\n",
" <td>9.983</td>\n",
" <td>4.72</td>\n",
" <td>77.69</td>\n",
" <td>298.05</td>\n",
" <td>26.08</td>\n",
" <td>0.1390</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" spkid pha H epoch_mjd e a i om \\\n",
"3510 3024715 Y 17.69 60400 0.9480 17.800 19.67 48.69 \n",
"6483 3434371 N 24.11 54767 0.9060 7.315 32.39 213.81 \n",
"11522 3683246 N 20.00 60400 0.9407 21.440 93.63 338.57 \n",
"15455 3766081 N 16.27 57742 0.9919 153.200 145.50 165.97 \n",
"17114 3799259 N 21.20 60400 0.9962 332.600 108.34 219.67 \n",
"19835 3840692 N 22.61 60400 0.9889 96.930 139.83 340.62 \n",
"20634 3843547 N 18.68 60400 0.7984 5.774 10.98 348.98 \n",
"20682 3843840 N 18.17 58729 0.9789 59.680 159.03 187.95 \n",
"20698 3843628 N 21.20 60400 0.7734 5.693 13.57 252.31 \n",
"20742 3843716 N 20.05 60400 0.7984 5.775 10.96 348.94 \n",
"22110 3989287 N 18.12 60400 0.9213 7.701 165.58 105.87 \n",
"28090 54240416 N 18.61 60400 0.8883 9.983 4.72 77.69 \n",
"\n",
" w ma moid \n",
"3510 333.32 117.04 0.0111 \n",
"6483 263.82 357.31 0.1090 \n",
"11522 311.75 35.25 0.4590 \n",
"15455 77.94 360.00 0.5970 \n",
"17114 151.26 0.39 0.3330 \n",
"19835 193.09 1.90 0.1010 \n",
"20634 57.12 114.87 0.2340 \n",
"20682 176.27 0.09 0.2580 \n",
"20698 75.55 122.88 0.3770 \n",
"20742 57.16 114.83 0.2330 \n",
"22110 57.80 66.15 0.0817 \n",
"28090 298.05 26.08 0.1390 "
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df['a']>5]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "11f926f6-ee7c-47f1-82ae-1c5299e219f3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(34864, 11)"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#We eliminate the values with a>5\n",
"df.drop(df[df['a']>5].index,inplace=True)\n",
"df.reset_index(drop=True,inplace=True)\n",
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "d1203169-ac0c-4d03-9dac-ebd136cd7680",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>spkid</th>\n",
" <th>H</th>\n",
" <th>epoch_mjd</th>\n",
" <th>e</th>\n",
" <th>a</th>\n",
" <th>i</th>\n",
" <th>om</th>\n",
" <th>w</th>\n",
" <th>ma</th>\n",
" <th>moid</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>3.486400e+04</td>\n",
" <td>34860.000000</td>\n",
" <td>34864.000000</td>\n",
" <td>34864.000000</td>\n",
" <td>34864.000000</td>\n",
" <td>34864.000000</td>\n",
" <td>34864.000000</td>\n",
" <td>34864.000000</td>\n",
" <td>34864.000000</td>\n",
" <td>3.486400e+04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>2.360419e+07</td>\n",
" <td>23.487377</td>\n",
" <td>59701.525298</td>\n",
" <td>0.437086</td>\n",
" <td>1.744036</td>\n",
" <td>11.983268</td>\n",
" <td>171.907288</td>\n",
" <td>182.575511</td>\n",
" <td>171.776436</td>\n",
" <td>8.546965e-02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>2.362906e+07</td>\n",
" <td>2.893991</td>\n",
" <td>1572.100889</td>\n",
" <td>0.176795</td>\n",
" <td>0.556275</td>\n",
" <td>10.567228</td>\n",
" <td>103.655813</td>\n",
" <td>104.304053</td>\n",
" <td>122.267979</td>\n",
" <td>9.826509e-02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>3.001703e+06</td>\n",
" <td>9.260000</td>\n",
" <td>44221.000000</td>\n",
" <td>0.002800</td>\n",
" <td>0.461700</td>\n",
" <td>0.010000</td>\n",
" <td>0.010000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>4.540000e-07</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>3.701855e+06</td>\n",
" <td>21.330000</td>\n",
" <td>59976.000000</td>\n",
" <td>0.304400</td>\n",
" <td>1.294000</td>\n",
" <td>4.420000</td>\n",
" <td>80.377500</td>\n",
" <td>93.367500</td>\n",
" <td>49.525000</td>\n",
" <td>1.280000e-02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>3.843818e+06</td>\n",
" <td>23.800000</td>\n",
" <td>60400.000000</td>\n",
" <td>0.451600</td>\n",
" <td>1.692000</td>\n",
" <td>8.490000</td>\n",
" <td>171.650000</td>\n",
" <td>184.545000</td>\n",
" <td>164.730000</td>\n",
" <td>4.520000e-02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>5.416727e+07</td>\n",
" <td>25.600000</td>\n",
" <td>60400.000000</td>\n",
" <td>0.564900</td>\n",
" <td>2.171000</td>\n",
" <td>16.802500</td>\n",
" <td>252.400000</td>\n",
" <td>272.662500</td>\n",
" <td>291.915000</td>\n",
" <td>1.280000e-01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>5.443990e+07</td>\n",
" <td>33.580000</td>\n",
" <td>60435.000000</td>\n",
" <td>0.970300</td>\n",
" <td>4.816000</td>\n",
" <td>154.350000</td>\n",
" <td>359.980000</td>\n",
" <td>359.960000</td>\n",
" <td>360.000000</td>\n",
" <td>7.080000e-01</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" spkid H epoch_mjd e a \\\n",
"count 3.486400e+04 34860.000000 34864.000000 34864.000000 34864.000000 \n",
"mean 2.360419e+07 23.487377 59701.525298 0.437086 1.744036 \n",
"std 2.362906e+07 2.893991 1572.100889 0.176795 0.556275 \n",
"min 3.001703e+06 9.260000 44221.000000 0.002800 0.461700 \n",
"25% 3.701855e+06 21.330000 59976.000000 0.304400 1.294000 \n",
"50% 3.843818e+06 23.800000 60400.000000 0.451600 1.692000 \n",
"75% 5.416727e+07 25.600000 60400.000000 0.564900 2.171000 \n",
"max 5.443990e+07 33.580000 60435.000000 0.970300 4.816000 \n",
"\n",
" i om w ma moid \n",
"count 34864.000000 34864.000000 34864.000000 34864.000000 3.486400e+04 \n",
"mean 11.983268 171.907288 182.575511 171.776436 8.546965e-02 \n",
"std 10.567228 103.655813 104.304053 122.267979 9.826509e-02 \n",
"min 0.010000 0.010000 0.000000 0.000000 4.540000e-07 \n",
"25% 4.420000 80.377500 93.367500 49.525000 1.280000e-02 \n",
"50% 8.490000 171.650000 184.545000 164.730000 4.520000e-02 \n",
"75% 16.802500 252.400000 272.662500 291.915000 1.280000e-01 \n",
"max 154.350000 359.980000 359.960000 360.000000 7.080000e-01 "
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.describe()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "17be8338-6c23-4cc9-ae08-d1ab7f705a79",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of PHAs: 2421\n",
"Percentage of PHAs: 6.944125745754933\n"
]
}
],
"source": [
"#Count the number of PHAs in the dataset\n",
"print(\"Number of PHAs:\", np.count_nonzero(df['pha']=='Y'))\n",
"print(\"Percentage of PHAs:\", 100*np.count_nonzero(df['pha']=='Y')/df.shape[0])"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "cafcc865-5058-4a84-932b-8dcf95a5dcd4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of asteroids with MOID=0: 0\n",
"Number of asteroids with MOID < 0.05: 18275\n"
]
}
],
"source": [
"#Number of asteroids with MOID=0 and MOID <0.05\n",
"print(\"Number of asteroids with MOID=0:\", len(df[df['moid']==0.0]))\n",
"print(\"Number of asteroids with MOID < 0.05:\", len(df[df['moid']<0.05]))"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "cb2545a2-9961-4118-a2e3-94647adc4d85",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#Correlation\n",
"corr=df[['a','e','i','om','w','ma','H']].corr() #computes the Pearson's correlation coefficients\n",
"sns.heatmap(corr,cmap='Blues',annot=True)\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "5ca71abd-e643-4c68-becf-881a3630504e",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1200x1200 with 16 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#Scatter matrix of a,e,i,H\n",
"from pandas.plotting import scatter_matrix\n",
"scatter_matrix(df[['a','e','i','H']],diagonal='kde',s=1,figsize=(12,12))\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "489f5e69-ca1b-4e09-b59c-5f09be65897b",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#Histogram of the MOID\n",
"num_bins=math.ceil(math.log2(len(df))+1) #Sturges rule\n",
"df['moid'].hist(bins=num_bins)\n",
"plt.xlabel('MOID')\n",
"plt.ylabel('count')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "d1ec49a8-4fa2-454b-aa17-841584aec502",
"metadata": {},
"outputs": [],
"source": [
"df.to_csv(folder+'neos_dataframe.csv')"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.9.19"
}
},
"nbformat": 4,
"nbformat_minor": 5
}