Sanjay
3 years ago
parent
799efa6284
commit
3b217365ac
File diff suppressed because one or more lines are too long
@ -0,0 +1,443 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"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>datetime</th>\n",
|
||||
" <th>city</th>\n",
|
||||
" <th>state</th>\n",
|
||||
" <th>country</th>\n",
|
||||
" <th>shape</th>\n",
|
||||
" <th>duration (seconds)</th>\n",
|
||||
" <th>duration (hours/min)</th>\n",
|
||||
" <th>comments</th>\n",
|
||||
" <th>date posted</th>\n",
|
||||
" <th>latitude</th>\n",
|
||||
" <th>longitude</th>\n",
|
||||
" </tr>\n",
|
||||
" </thead>\n",
|
||||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>0</th>\n",
|
||||
" <td>10/10/1949 20:30</td>\n",
|
||||
" <td>san marcos</td>\n",
|
||||
" <td>tx</td>\n",
|
||||
" <td>us</td>\n",
|
||||
" <td>cylinder</td>\n",
|
||||
" <td>2700.0</td>\n",
|
||||
" <td>45 minutes</td>\n",
|
||||
" <td>This event took place in early fall around 194...</td>\n",
|
||||
" <td>4/27/2004</td>\n",
|
||||
" <td>29.883056</td>\n",
|
||||
" <td>-97.941111</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1</th>\n",
|
||||
" <td>10/10/1949 21:00</td>\n",
|
||||
" <td>lackland afb</td>\n",
|
||||
" <td>tx</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>light</td>\n",
|
||||
" <td>7200.0</td>\n",
|
||||
" <td>1-2 hrs</td>\n",
|
||||
" <td>1949 Lackland AFB&#44 TX. Lights racing acros...</td>\n",
|
||||
" <td>12/16/2005</td>\n",
|
||||
" <td>29.384210</td>\n",
|
||||
" <td>-98.581082</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>2</th>\n",
|
||||
" <td>10/10/1955 17:00</td>\n",
|
||||
" <td>chester (uk/england)</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>gb</td>\n",
|
||||
" <td>circle</td>\n",
|
||||
" <td>20.0</td>\n",
|
||||
" <td>20 seconds</td>\n",
|
||||
" <td>Green/Orange circular disc over Chester&#44 En...</td>\n",
|
||||
" <td>1/21/2008</td>\n",
|
||||
" <td>53.200000</td>\n",
|
||||
" <td>-2.916667</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>3</th>\n",
|
||||
" <td>10/10/1956 21:00</td>\n",
|
||||
" <td>edna</td>\n",
|
||||
" <td>tx</td>\n",
|
||||
" <td>us</td>\n",
|
||||
" <td>circle</td>\n",
|
||||
" <td>20.0</td>\n",
|
||||
" <td>1/2 hour</td>\n",
|
||||
" <td>My older brother and twin sister were leaving ...</td>\n",
|
||||
" <td>1/17/2004</td>\n",
|
||||
" <td>28.978333</td>\n",
|
||||
" <td>-96.645833</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>4</th>\n",
|
||||
" <td>10/10/1960 20:00</td>\n",
|
||||
" <td>kaneohe</td>\n",
|
||||
" <td>hi</td>\n",
|
||||
" <td>us</td>\n",
|
||||
" <td>light</td>\n",
|
||||
" <td>900.0</td>\n",
|
||||
" <td>15 minutes</td>\n",
|
||||
" <td>AS a Marine 1st Lt. flying an FJ4B fighter/att...</td>\n",
|
||||
" <td>1/22/2004</td>\n",
|
||||
" <td>21.418056</td>\n",
|
||||
" <td>-157.803611</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"</div>"
|
||||
],
|
||||
"text/plain": [
|
||||
" datetime city state country shape \\\n",
|
||||
"0 10/10/1949 20:30 san marcos tx us cylinder \n",
|
||||
"1 10/10/1949 21:00 lackland afb tx NaN light \n",
|
||||
"2 10/10/1955 17:00 chester (uk/england) NaN gb circle \n",
|
||||
"3 10/10/1956 21:00 edna tx us circle \n",
|
||||
"4 10/10/1960 20:00 kaneohe hi us light \n",
|
||||
"\n",
|
||||
" duration (seconds) duration (hours/min) \\\n",
|
||||
"0 2700.0 45 minutes \n",
|
||||
"1 7200.0 1-2 hrs \n",
|
||||
"2 20.0 20 seconds \n",
|
||||
"3 20.0 1/2 hour \n",
|
||||
"4 900.0 15 minutes \n",
|
||||
"\n",
|
||||
" comments date posted latitude \\\n",
|
||||
"0 This event took place in early fall around 194... 4/27/2004 29.883056 \n",
|
||||
"1 1949 Lackland AFB, TX. Lights racing acros... 12/16/2005 29.384210 \n",
|
||||
"2 Green/Orange circular disc over Chester, En... 1/21/2008 53.200000 \n",
|
||||
"3 My older brother and twin sister were leaving ... 1/17/2004 28.978333 \n",
|
||||
"4 AS a Marine 1st Lt. flying an FJ4B fighter/att... 1/22/2004 21.418056 \n",
|
||||
"\n",
|
||||
" longitude \n",
|
||||
"0 -97.941111 \n",
|
||||
"1 -98.581082 \n",
|
||||
"2 -2.916667 \n",
|
||||
"3 -96.645833 \n",
|
||||
"4 -157.803611 "
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"ufos = pd.read_csv(\"C:\\\\Users\\\\Admin\\\\OneDrive\\\\Desktop\\\\AI\\\\ML google\\\\ML-For-Beginners\\\\3-Web-App\\\\1-Web-App\\\\data\\\\ufos.csv\")\n",
|
||||
"ufos.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"array(['us', nan, 'gb', 'ca', 'au', 'de'], dtype=object)"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"ufos = pd.DataFrame({'Seconds': ufos['duration (seconds)'], 'Country': ufos['country'],'Latitude': ufos['latitude'],'Longitude': ufos['longitude']})\n",
|
||||
"\n",
|
||||
"ufos.Country.unique()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||||
"Int64Index: 25863 entries, 2 to 80330\n",
|
||||
"Data columns (total 4 columns):\n",
|
||||
" # Column Non-Null Count Dtype \n",
|
||||
"--- ------ -------------- ----- \n",
|
||||
" 0 Seconds 25863 non-null float64\n",
|
||||
" 1 Country 25863 non-null object \n",
|
||||
" 2 Latitude 25863 non-null float64\n",
|
||||
" 3 Longitude 25863 non-null float64\n",
|
||||
"dtypes: float64(3), object(1)\n",
|
||||
"memory usage: 1010.3+ KB\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"ufos.dropna(inplace=True)\n",
|
||||
"\n",
|
||||
"ufos = ufos[(ufos['Seconds'] >= 1) & (ufos['Seconds'] <= 60)]\n",
|
||||
"\n",
|
||||
"ufos.info()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"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>Seconds</th>\n",
|
||||
" <th>Country</th>\n",
|
||||
" <th>Latitude</th>\n",
|
||||
" <th>Longitude</th>\n",
|
||||
" </tr>\n",
|
||||
" </thead>\n",
|
||||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>2</th>\n",
|
||||
" <td>20.0</td>\n",
|
||||
" <td>3</td>\n",
|
||||
" <td>53.200000</td>\n",
|
||||
" <td>-2.916667</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>3</th>\n",
|
||||
" <td>20.0</td>\n",
|
||||
" <td>4</td>\n",
|
||||
" <td>28.978333</td>\n",
|
||||
" <td>-96.645833</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>14</th>\n",
|
||||
" <td>30.0</td>\n",
|
||||
" <td>4</td>\n",
|
||||
" <td>35.823889</td>\n",
|
||||
" <td>-80.253611</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>23</th>\n",
|
||||
" <td>60.0</td>\n",
|
||||
" <td>4</td>\n",
|
||||
" <td>45.582778</td>\n",
|
||||
" <td>-122.352222</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>24</th>\n",
|
||||
" <td>3.0</td>\n",
|
||||
" <td>3</td>\n",
|
||||
" <td>51.783333</td>\n",
|
||||
" <td>-0.783333</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"</div>"
|
||||
],
|
||||
"text/plain": [
|
||||
" Seconds Country Latitude Longitude\n",
|
||||
"2 20.0 3 53.200000 -2.916667\n",
|
||||
"3 20.0 4 28.978333 -96.645833\n",
|
||||
"14 30.0 4 35.823889 -80.253611\n",
|
||||
"23 60.0 4 45.582778 -122.352222\n",
|
||||
"24 3.0 3 51.783333 -0.783333"
|
||||
]
|
||||
},
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from sklearn.preprocessing import LabelEncoder\n",
|
||||
"\n",
|
||||
"ufos['Country'] = LabelEncoder().fit_transform(ufos['Country'])\n",
|
||||
"\n",
|
||||
"ufos.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"\n",
|
||||
"Selected_features = ['Seconds','Latitude','Longitude']\n",
|
||||
"\n",
|
||||
"X = ufos[Selected_features]\n",
|
||||
"y = ufos['Country']\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 1.00 1.00 1.00 41\n",
|
||||
" 1 0.83 0.21 0.34 250\n",
|
||||
" 2 1.00 1.00 1.00 8\n",
|
||||
" 3 1.00 1.00 1.00 131\n",
|
||||
" 4 0.96 1.00 0.98 4743\n",
|
||||
"\n",
|
||||
" accuracy 0.96 5173\n",
|
||||
" macro avg 0.96 0.84 0.86 5173\n",
|
||||
"weighted avg 0.96 0.96 0.95 5173\n",
|
||||
"\n",
|
||||
"Predicted labels: [4 4 4 ... 3 4 4]\n",
|
||||
"Accuracy: 0.9597912236613184\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"c:\\Users\\Admin\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
|
||||
"STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
|
||||
"\n",
|
||||
"Increase the number of iterations (max_iter) or scale the data as shown in:\n",
|
||||
" https://scikit-learn.org/stable/modules/preprocessing.html\n",
|
||||
"Please also refer to the documentation for alternative solver options:\n",
|
||||
" https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
|
||||
" n_iter_i = _check_optimize_result(\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"from sklearn.metrics import accuracy_score, classification_report \n",
|
||||
"from sklearn.linear_model import LogisticRegression\n",
|
||||
"model = LogisticRegression()\n",
|
||||
"model.fit(X_train, y_train)\n",
|
||||
"predictions = model.predict(X_test)\n",
|
||||
"\n",
|
||||
"print(classification_report(y_test, predictions))\n",
|
||||
"print('Predicted labels: ', predictions)\n",
|
||||
"print('Accuracy: ', accuracy_score(y_test, predictions))\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[1]\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"c:\\Users\\Admin\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:409: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
|
||||
" warnings.warn(\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import pickle\n",
|
||||
"model_filename = 'ufo-model.pkl'\n",
|
||||
"pickle.dump(model, open(model_filename,'wb'))\n",
|
||||
"\n",
|
||||
"model = pickle.load(open('ufo-model.pkl','rb'))\n",
|
||||
"print(model.predict([[50,44,-12]]))\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.11.1"
|
||||
},
|
||||
"orig_nbformat": 4,
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "72b2382ece9768098284d92bbc69d35954e75b60d1e25897d1389c232f4796f0"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Loading…
Reference in new issue