Cleanup git

.gitignore

 # .gitignore
 
-sas2/
\ No newline at end of file
+sas2/
+.idea/
\ No newline at end of file

.~lock.diamonds.csv#

-,fadi,hp,21.12.2023 18:45,file:///home/fadi/.config/libreoffice/4;
\ No newline at end of file

DisplayWindow.py → Main.py

@@ -78,9 +78,6 @@ class MainWindow(QMainWindow):
         self.GUI_selections = {}
         # create new graphs
         self.scatt = MplCanvas(self, width=6, height=5, dpi=100)
-        self.scatt.axes.set_title("Carats vs Price")
-        self.scatt.axes.scatter(diamonds['carat'], diamonds['price'], color='red', s=2)
-
         # Create labels and input fields
         self.input_fields = [QComboBox(self), QComboBox(self), QComboBox(self), QLineEdit(self),
                              QLineEdit(self), QLineEdit(self), QLineEdit(self), QLineEdit(self),
@@ -113,6 +110,11 @@ class MainWindow(QMainWindow):
         self.setWindowTitle('Assistance Systems')
         self.show()
 
+    def update_graph(self):
+        self.scatt.axes.set_title("Carats vs Price")
+        self.scatt.axes.scatter(diamonds['carat'], diamonds['price'], color='red', s=2)
+        # self.scatt.axes.scatter(self.GUI_selections['carat'], self.price, color='blue', s=50)
+    
     def disable_input_field(self, field_name):
         for key, value in self.menu_items.items():
             if value == field_name:
@@ -148,7 +150,7 @@ class MainWindow(QMainWindow):
         self.price = model.predict_price(X_test)
         # price = model.predict(X_test)[0]
         self.display_price.setText(str(self.price))
-
+        self.update_graph()
 
     def validate_inputs(self, val, attribute):
         if Advanced.Advanced_selections[attribute]:
@@ -291,4 +293,4 @@ app = QApplication(sys.argv)
 
 window = MyTabs()
 window.show()
-app.exec()
+app.exec()
\ No newline at end of file

data_processing.py

-import pandas as pd
-from sklearn.model_selection import train_test_split
-
-class DataPreprocessor:
-    def __init__(self, filepath):
-        self.filepath = filepath
-        self.data = pd.read_csv(filepath) 
-
-    def clean_data(self):
-        self.data = self.data.dropna(inplace=True)
-
-    @staticmethod
-    def convert_to_numeric(self):
-        self['cut'] = self['cut'].map({'Ideal': 5, 'Premium': 4, 'Very Good': 3, 'Good': 2, 'Fair': 1})
-        self['color'] = self['color'].map({'D': 7, 'E': 6, 'F': 5, 'G': 4, 'H': 3, 'I': 2, 'J': 1})
-        self['clarity'] = self['clarity'].map({'IF': 8, 'VVS1': 7, 'VVS2': 6, 'VS1': 5, 'VS2': 4, 'SI1': 3, 'SI2': 2,
-                                               'I1': 1})
-    
-    def get_X(self):
-        return self.data.drop('price', axis=1)
-    
-    def get_y(self):
-        return self.data['price']
-
-    def split_data(X, y):
-        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-        return X_train, X_test, y_train, y_test
-
-

old/airlines.json

-["Endeavor Air Inc.", "JetBlue Airways", "ExpressJet Airlines Inc.", "Allegiant Air", "Hawaiian Airlines Inc.", "Spirit Air Lines", "SkyWest Airlines Inc.", "Frontier Airlines Inc.", "Empire Airlines Inc.", "Southwest Airlines Co.", "Mesa Airlines Inc.", "Republic Airlines", "Delta Air Lines Inc.", "United Air Lines Inc.", "Alaska Airlines Inc.", "Horizon Air", "Commutair Aka Champlain Enterprises, Inc.", "Trans States Airlines", "GoJet Airlines, LLC d/b/a United Express", "Air Wisconsin Airlines Corp", "Cape Air", "Compass Airlines", "Virgin America", "Peninsula Airways Inc.", "Envoy Air", "American Airlines Inc.", "Comair Inc.", "Capital Cargo International"]
\ No newline at end of file

old/destination_cities.json

-["Atlanta, GA", "Albany, GA", "Mobile, AL", "Evansville, IN", "Detroit, MI", "Jacksonville/Camp Lejeune, NC", "Boston, MA", "Syracuse, NY", "New Bern/Morehead/Beaufort, NC", "Montgomery, AL", "New York, NY", "Minneapolis, MN", "Cleveland, OH", "Charlotte, NC", "Fayetteville, NC", "St. Louis, MO", "Columbus, OH", "Indianapolis, IN", "Knoxville, TN", "Mosinee, WI", "Alexandria, LA", "Killeen, TX", "San Antonio, TX", "Peoria, IL", "Houston, TX", "Dallas/Fort Worth, TX", "Richmond, VA", "Portland, ME", "Kalamazoo, MI", "Cincinnati, OH", "Bristol/Johnson City/Kingsport, TN", "Washington, DC", "Asheville, NC", "Baton Rouge, LA", "Buffalo, NY", "Grand Rapids, MI", "Bismarck/Mandan, ND", "Chattanooga, TN", "Traverse City, MI", "Fort Smith, AR", "Burlington, VT", "Kansas City, MO", "Green Bay, WI", "Tulsa, OK", "Valdosta, GA", "Charleston/Dunbar, WV", "Fayetteville, AR", "Rochester, NY", "Savannah, GA", "Roanoke, VA", "Harrisburg, PA", "New Orleans, LA", "Nashville, TN", "Raleigh/Durham, NC", "Milwaukee, WI", "Gainesville, FL", "Tampa, FL", "Greensboro/High Point, NC", "Charlottesville, VA", "Bangor, ME", "Grand Forks, ND", "Brunswick, GA", "Memphis, TN", "Wilmington, NC", "Bloomington/Normal, IL", "Norfolk, VA", "Manchester, NH", "Dayton, OH", "Greer, SC", "Lexington, KY", "Louisville, KY", "Hartford, CT", "Saginaw/Bay City/Midland, MI", "Minot, ND", "Columbia, SC", "Columbus, GA", "Des Moines, IA", "Dothan, AL", "Elmira/Corning, NY", "Pittsburgh, PA", "Jacksonville, FL", "Chicago, IL", "Springfield, MO", "Shreveport, LA", "Huntsville, AL", "Omaha, NE", "Tallahassee, FL", "Madison, WI", "Lansing, MI", "Baltimore, MD", "Charleston, SC", "Little Rock, AR", "Fort Myers, FL", "Orlando, FL", "Fargo, ND", "Appleton, WI", "Akron, OH", "Harlingen/San Benito, TX", "White Plains, NY", "Philadelphia, PA", "Moline, IL", "Aguadilla, PR", "San Francisco, CA", "Newark, NJ", "Fort Lauderdale, FL", "Salt Lake City, UT", "Ponce, PR", "San Jose, CA", "Long Beach, CA", "Las Vegas, NV", "Los Angeles, CA", "West Palm Beach/Palm Beach, FL", "San Juan, PR", "Sarasota/Bradenton, FL", "Austin, TX", "Newburgh/Poughkeepsie, NY", "Denver, CO", "Seattle, WA", "Providence, RI", "Sacramento, CA", "Charlotte Amalie, VI", "Portland, OR", "Worcester, MA", "San Diego, CA", "Reno, NV", "Albany, NY", "Phoenix, AZ", "Oakland, CA", "Palm Springs, CA", "Christiansted, VI", "Burbank, CA", "Daytona Beach, FL", "Albuquerque, NM", "Brownsville, TX", "El Paso, TX", "Oklahoma City, OK", "Gulfport/Biloxi, MS", "South Bend, IN", "Mission/McAllen/Edinburg, TX", "Lake Charles, LA", "Lafayette, LA", "Myrtle Beach, SC", "Rochester, MN", "Lincoln, NE", "Birmingham, AL", "Augusta, GA", "Jackson/Vicksburg, MS", "Cedar Rapids/Iowa City, IA", "Panama City, FL", "Valparaiso, FL", "Key West, FL", "Allentown/Bethlehem/Easton, PA", "Sanford, FL", "Billings, MT", "Flint, MI", "Missoula, MT", "Idaho Falls, ID", "Stockton, CA", "Toledo, OH", "Sioux Falls, SD", "Ashland, WV", "Fresno, CA", "Eugene, OR", "Bellingham, WA", "Punta Gorda, FL", "St. Cloud, MN", "St. Petersburg, FL", "Plattsburgh, NY", "Ogdensburg, NY", "Concord, NC", "Springfield, IL", "Provo, UT", "Montrose/Delta, CO", "Fort Wayne, IN", "Portsmouth, NH", "Trenton, NJ", "Niagara Falls, NY", "Belleville, IL", "Rockford, IL", "Ogden, UT", "Boise, ID", "Medford, OR", "Great Falls, MT", "Pasco/Kennewick/Richland, WA", "Wichita, KS", "Grand Island, NE", "Monterey, CA", "Grand Junction, CO", "Laredo, TX", "Rapid City, SD", "Kalispell, MT", "Santa Maria, CA", "Bozeman, MT", "Hagerstown, MD", "Clarksburg/Fairmont, WV", "Colorado Springs, CO", "Owensboro, KY", "Honolulu, HI", "Kahului, HI", "Kona, HI", "Lihue, HI", "Hilo, HI", "Columbia, MO", "Casper, WY", "Scranton/Wilkes-Barre, PA", "Tucson, AZ", "Bend/Redmond, OR", "Santa Barbara, CA", "Aspen, CO", "Ontario, CA", "Helena, MT", "Sun Valley/Hailey/Ketchum, ID", "Durango, CO", "Williston, ND", "Arcata/Eureka, CA", "San Luis Obispo, CA", "Mammoth Lakes, CA", "Spokane, WA", "Jackson, WY", "Santa Rosa, CA", "Santa Ana, CA", "Redding, CA", "Bakersfield, CA", "Hayden, CO", "Midland/Odessa, TX", "Ithaca/Cortland, NY", "Lewiston, ID", "Pocatello, ID", "Aberdeen, SD", "Cody, WY", "Alpena, MI", "Escanaba, MI", "Pellston, MI", "Bemidji, MN", "Brainerd, MN", "Butte, MT", "Cedar City, UT", "St. George, UT", "Sault Ste. Marie, MI", "Marquette, MI", "Elko, NV", "Hibbing, MN", "Binghamton, NY", "Twin Falls, ID", "Rhinelander, WI", "International Falls, MN", "Iron Mountain/Kingsfd, MI", "Dallas, TX", "Columbus, MS", "Monroe, LA", "State College, PA", "Erie, PA", "La Crosse, WI", "Duluth, MN", "Muskegon, MI", "Pueblo, CO", "Hancock/Houghton, MI", "Paducah, KY", "Quincy, IL", "Rock Springs, WY", "Jamestown, ND", "Devils Lake, ND", "Laramie, WY", "Gillette, WY", "Eau Claire, WI", "Hays, KS", "Eagle, CO", "Cape Girardeau, MO", "North Bend/Coos Bay, OR", "Amarillo, TX", "Miami, FL", "Islip, NY", "Pago Pago, TT", "Hoolehua, HI", "Lanai, HI", "Kapalua, HI", "Atlantic City, NJ", "Latrobe, PA", "Lubbock, TX", "Pensacola, FL", "Corpus Christi, TX", "Melbourne, FL", "Fairbanks, AK", "Anchorage, AK", "Newport News/Williamsburg, VA", "Guam, TT", "Gunnison, CO", "Bethel, AK", "Kodiak, AK", "Deadhorse, AK", "Barrow, AK", "Ketchikan, AK", "Juneau, AK", "Sitka, AK", "Petersburg, AK", "Wrangell, AK", "Nome, AK", "Kotzebue, AK", "Yakutat, AK", "Cordova, AK", "Adak Island, AK", "Yakima, WA", "Santa Fe, NM", "Champaign/Urbana, IL", "Dickinson, ND", "Saipan, TT", "Rota, TT", "Walla Walla, WA", "Wenatchee, WA", "Pullman, WA", "College Station/Bryan, TX", "Hobbs, NM", "Youngstown/Warren, OH", "Unalaska, AK", "Scottsbluff, NE", "Nantucket, MA", "Martha's Vineyard, MA", "Branson, MO", "Tyler, TX", "San Angelo, TX", "Wichita Falls, TX", "Beaumont/Port Arthur, TX", "Lawton/Fort Sill, OK", "Waco, TX", "Flagstaff, AZ", "Yuma, AZ", "Meridian, MS", "Hattiesburg/Laurel, MS", "Roswell, NM", "Kearney, NE", "Moab, UT", "Vernal, UT", "Lewisburg, WV", "Staunton, VA", "Salina, KS", "Liberal, KS", "North Platte, NE", "Prescott, AZ", "Abilene, TX", "Manhattan/Ft. Riley, KS", "Texarkana, AR", "Lynchburg, VA", "Greenville, NC", "New Haven, CT", "Presque Isle/Houlton, ME", "Hilton Head, SC", "Longview, TX", "Waterloo, IA", "Sioux City, IA", "Dubuque, IA", "Garden City, KS", "Salisbury, MD", "Williamsport, PA", "Florence, SC", "Stillwater, OK", "Joplin, MO", "Watertown, NY", "Cheyenne, WY", "Del Rio, TX", "Hyannis, MA", "Dillingham, AK", "King Salmon, AK", "Gustavus, AK", "West Yellowstone, MT"]
\ No newline at end of file

requirements.txt

+asttokens==2.4.1
+comm==0.2.0
+contourpy==1.2.0
+cycler==0.12.1
+debugpy==1.8.0
+decorator==5.1.1
+exceptiongroup==1.2.0
+executing==2.0.1
+fonttools==4.46.0
+ipykernel==6.27.1
+ipython==8.18.1
+jedi==0.19.1
+joblib==1.3.2
+jupyter_client==8.6.0
+jupyter_core==5.5.0
+kiwisolver==1.4.5
+lightgbm==4.1.0
+Markdown==3.5.1
+matplotlib==3.8.2
+matplotlib-inline==0.1.6
+nest-asyncio==1.5.8
+numpy==1.26.2
+packaging==23.2
+pandas==2.1.4
+parso==0.8.3
+pexpect==4.9.0
+Pillow==10.1.0
+platformdirs==4.1.0
+prompt-toolkit==3.0.41
+psutil==5.9.6
+ptyprocess==0.7.0
+pure-eval==0.2.2
+Pygments==2.17.2
+pyparsing==3.1.1
+PyQt6==6.6.1
+PyQt6-Qt6==6.6.1
+PyQt6-sip==13.6.0
+pyqtgraph==0.13.3
+python-dateutil==2.8.2
+pytz==2023.3.post1
+pyzmq==25.1.2
+qtgui==0.0.1
+qtwidgets==1.1
+scikit-learn==1.3.2
+scipy==1.11.4
+six==1.16.0
+stack-data==0.6.3
+threadpoolctl==3.2.0
+tornado==6.4
+traitlets==5.14.0
+tzdata==2023.3
+wcwidth==0.2.12
+xgboost==2.0.3

training.ipynb

-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-12-11T17:07:26.744932200Z",
-     "start_time": "2023-12-11T17:07:26.740214500Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "import sklearn as sk\n",
-    "import matplotlib.pyplot as plt\n",
-    "import json\n",
-    "import math"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-12-11T17:07:55.590798700Z",
-     "start_time": "2023-12-11T17:07:26.744932200Z"
-    }
-   },
-   "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 'pd' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[2], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m cf_2018 \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mflight_data/Combined_Flights_2019.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m      2\u001b[0m cf_2018\u001b[38;5;241m.\u001b[39mhead()\n",
-      "\u001b[0;31mNameError\u001b[0m: name 'pd' is not defined"
-     ]
-    }
-   ],
-   "source": [
-    "cf_2018 = pd.read_csv('flight_data/Combined_Flights_2018.csv')\n",
-    "cf_2019 = pd.read_csv('flight_data/Combined_Flights_2019.csv')\n",
-    "cf_2018.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-12-11T17:07:56.493778700Z",
-     "start_time": "2023-12-11T17:07:55.953264900Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "# Filter the dataframe to include only the delays from JFK\n",
-    "import RegressionModel\n",
-    "\n",
-    "filtered_df = cf_2018[(cf_2018['Origin'] == 'JFK')].copy()\n",
-    "\n",
-    "RegressionModel.destinations = list(cf_2018['DestCityName'].unique())\n",
-    "\n",
-    "filtered_df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-12-11T17:07:56.527530200Z",
-     "start_time": "2023-12-11T17:07:56.498869700Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "relevant_columns = ['FlightDate', 'DOT_ID_Operating_Airline', 'DestAirportID', 'DepDelayMinutes', 'ArrDelayMinutes']\n",
-    "jfk_flights_2018 = filtered_df[relevant_columns].copy()\n",
-    "jfk_flights_2018.dropna(inplace=True)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-12-11T17:07:56.542402200Z",
-     "start_time": "2023-12-11T17:07:56.526530600Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "jfk_flights_2018"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-12-11T17:07:56.666500700Z",
-     "start_time": "2023-12-11T17:07:56.546471Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "# Convert 'FlightDate' into numerical components\n",
-    "jfk_flights_2018['FlightDate'] = pd.to_datetime(jfk_flights_2018['FlightDate'])\n",
-    "jfk_flights_2018['Year'] = jfk_flights_2018['FlightDate'].dt.year\n",
-    "jfk_flights_2018['Month'] = jfk_flights_2018['FlightDate'].dt.month\n",
-    "jfk_flights_2018['Day'] = jfk_flights_2018['FlightDate'].dt.day\n",
-    "\n",
-    "jfk_flights_2018 = jfk_flights_2018.dropna()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-12-11T17:07:56.737639800Z",
-     "start_time": "2023-12-11T17:07:56.666500700Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from sklearn.model_selection import train_test_split\n",
-    "\n",
-    "# Choose your target variable, e.g., 'DepDelayMinutes'\n",
-    "X = jfk_flights_2018.drop('DepDelayMinutes', axis=1)\n",
-    "y = jfk_flights_2018['DepDelayMinutes']\n",
-    "\n",
-    "jfk_flights_2018"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "\n",
-    "# Splitting the dataset into training and testing sets\n",
-    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
-    "\n",
-    "X_train = X_train.apply(pd.to_numeric, errors='coerce')\n",
-    "y_train = y_train.apply(pd.to_numeric, errors='coerce')\n",
-    "X_test = X_test.apply(pd.to_numeric, errors='coerce')\n",
-    "y_test = y_test.apply(pd.to_numeric, errors='coerce')\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-12-11T17:07:57.060977300Z",
-     "start_time": "2023-12-11T17:07:56.738640200Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from sklearn.linear_model import LinearRegression\n",
-    "\n",
-    "# Initialize the model\n",
-    "model = LinearRegression()\n",
-    "\n",
-    "# Train the model\n",
-    "model.fit(X_train, y_train)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-12-11T17:08:11.323526900Z",
-     "start_time": "2023-12-11T17:08:10.881732300Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from sklearn.metrics import mean_squared_error, r2_score\n",
-    "\n",
-    "# Predict on the test set\n",
-    "y_pred = model.predict(X_test)\n",
-    "\n",
-    "# Evaluate the model\n",
-    "mse = mean_squared_error(y_test, y_pred)\n",
-    "r2 = r2_score(y_test, y_pred)\n",
-    "print(\"Mean Squared Error:\", mse)\n",
-    "print(\"R^2 Score:\", r2)\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "sas2",
-   "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": "3.10.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

training3 copy.ipynb

-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "initial_id",
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 2
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}