Glucose_Regression_with_n_runs.ipynb

{"nbformat":4,"nbformat_minor":0,"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":"3.7.6"},"colab":{"name":"Glucose_Regression_with_n_runs.ipynb","provenance":[]}},"cells":[{"cell_type":"markdown","metadata":{"id":"Fq8SUgQFXG8L"},"source":["# **Glucose Regression**\n","\n"]},{"cell_type":"markdown","metadata":{"id":"MOG6rYfmXckI"},"source":["### Google Colab Functions"]},{"cell_type":"markdown","metadata":{"id":"IYtWMzOvLQ3s"},"source":["#### Prevent random disconnects\n","\n","This cell runs JS code to automatic reconnect to runtime."]},{"cell_type":"code","metadata":{"id":"jtClEMAMLVHw","colab":{"base_uri":"https://localhost:8080/","height":35},"executionInfo":{"status":"ok","timestamp":1625491890858,"user_tz":-330,"elapsed":14,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"c9ec07be-3df8-4bda-dc2a-2d1c18a7584a"},"source":["import IPython\n","from google.colab import output\n","\n","display(IPython.display.Javascript('''\n"," function ClickConnect(){\n","   btn = document.querySelector(\"colab-connect-button\")\n","   if (btn != null){\n","     console.log(\"Click colab-connect-button\"); \n","     btn.click() \n","     }\n","   \n","   btn = document.getElementById('ok')\n","   if (btn != null){\n","     console.log(\"Click reconnect\"); \n","     btn.click() \n","     }\n","  }\n","  \n","setInterval(ClickConnect,60000)\n","'''))\n","\n","print(\"Done.\")"],"execution_count":1,"outputs":[{"output_type":"display_data","data":{"application/javascript":["\n"," function ClickConnect(){\n","   btn = document.querySelector(\"colab-connect-button\")\n","   if (btn != null){\n","     console.log(\"Click colab-connect-button\"); \n","     btn.click() \n","     }\n","   \n","   btn = document.getElementById('ok')\n","   if (btn != null){\n","     console.log(\"Click reconnect\"); \n","     btn.click() \n","     }\n","  }\n","  \n","setInterval(ClickConnect,60000)\n"],"text/plain":["<IPython.core.display.Javascript object>"]},"metadata":{"tags":[]}},{"output_type":"stream","text":["Done.\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"A-SZElzHXpWi","executionInfo":{"status":"ok","timestamp":1625491912470,"user_tz":-330,"elapsed":21622,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"83e0a3eb-7c8a-4c2b-c7e1-9b633698bb2a"},"source":["from google.colab import drive\n","drive.mount('/gdrive')"],"execution_count":2,"outputs":[{"output_type":"stream","text":["Mounted at /gdrive\n"],"name":"stdout"}]},{"cell_type":"markdown","metadata":{"id":"JSEdsyEHW-fx"},"source":["# Libraries Used"]},{"cell_type":"code","metadata":{"id":"vev5Bdn3W-f0","executionInfo":{"status":"ok","timestamp":1625491913119,"user_tz":-330,"elapsed":652,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["# Imports\n","import pandas as pd\n","import numpy as np\n","import matplotlib.pyplot as plt\n","import seaborn as sns\n","from sklearn.model_selection import KFold\n","from sklearn.model_selection import cross_val_score\n","from sklearn.metrics import fbeta_score, make_scorer\n","from scipy.stats import norm\n"],"execution_count":3,"outputs":[]},{"cell_type":"code","metadata":{"id":"7awZBWvlW-f1","executionInfo":{"status":"ok","timestamp":1625491913792,"user_tz":-330,"elapsed":677,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["# Importing Dataset into Notebook\n","dataset =  pd.read_csv(\"/gdrive/MyDrive/Diabetes.csv\")"],"execution_count":4,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"q7rC76V2OTZh"},"source":["\n","# Data Analysis and Data Cleaning\n","\n","After importing the data, a simple analysis of the data is done."]},{"cell_type":"markdown","metadata":{"id":"1UiZ5Uzkfkgo"},"source":["Dropping the column \"id\" since it consists of unique value."]},{"cell_type":"code","metadata":{"id":"0zlRb8z4W-f4","executionInfo":{"status":"ok","timestamp":1625491913792,"user_tz":-330,"elapsed":11,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["dataset.drop(columns = \"id\",inplace=True)"],"execution_count":5,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"ls6YqAd1W-f5"},"source":["### Filling NAN Values as median of that columns"]},{"cell_type":"code","metadata":{"id":"qmlXNBG1W-f5","executionInfo":{"status":"ok","timestamp":1625491913793,"user_tz":-330,"elapsed":10,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["dataset[\"weight\"].fillna(dataset[\"weight\"].median(),inplace=True)\n","dataset[\"height\"].fillna(dataset[\"height\"].median(),inplace=True)\n","dataset[\"hdl\"].fillna(dataset[\"hdl\"].median(),inplace=True)\n","dataset[\"ratio\"].fillna(dataset[\"ratio\"].median(),inplace=True)\n","dataset[\"bp.1s\"].fillna(dataset[\"bp.1s\"].median(),inplace=True)\n","dataset[\"bp.1d\"].fillna(dataset[\"bp.1d\"].median(),inplace=True)\n","dataset[\"chol\"].fillna(dataset[\"chol\"].median(),inplace=True)\n","dataset[\"waist\"].fillna(dataset[\"waist\"].median(),inplace=True)\n","dataset[\"hip\"].fillna(dataset[\"hip\"].median(),inplace=True)\n","dataset[\"time.ppn\"].fillna(dataset[\"time.ppn\"].median(),inplace=True)\n","dataset[\"frame\"].fillna(\"medium\",inplace=True)\n","dataset[\"glyhb\"].fillna(dataset[\"glyhb\"].median(),inplace=True)\n"],"execution_count":6,"outputs":[]},{"cell_type":"code","metadata":{"id":"Cl1_5_55ZrOD","executionInfo":{"status":"ok","timestamp":1625491913793,"user_tz":-330,"elapsed":10,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["# Deleting bp.2s , bp.2d Too many NAN values so dropping values\n","dataset.drop(columns=[\"bp.2s\",\"bp.2d\"],inplace=True)"],"execution_count":7,"outputs":[]},{"cell_type":"code","metadata":{"id":"-7amaJFJW-f-","executionInfo":{"status":"ok","timestamp":1625491913793,"user_tz":-330,"elapsed":10,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["dataset[\"bp.1s\"] = np.log(dataset[\"bp.1s\"]) \n","dataset[\"hdl\"] = np.log(dataset[\"hdl\"]) \n","dataset[\"height\"] = np.log(dataset[\"height\"]) \n","dataset[\"age\"] = np.log(dataset[\"age\"]) \n","dataset[\"bp.1d\"] = np.log(dataset[\"bp.1d\"]) \n","dataset[\"ratio\"] = np.log(dataset[\"ratio\"]) \n","dataset[\"stab.glu\"] = np.sqrt(dataset[\"stab.glu\"])"],"execution_count":8,"outputs":[]},{"cell_type":"code","metadata":{"id":"bVNczEFxW-f_","executionInfo":{"status":"ok","timestamp":1625491913794,"user_tz":-330,"elapsed":9,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["from sklearn.preprocessing import StandardScaler,MinMaxScaler,RobustScaler\n","sc = StandardScaler()\n","dataset[\"stab.glu\"] =  sc.fit_transform(dataset[\"stab.glu\"].values.reshape(403,1))\n","dataset['hdl'] = sc.fit_transform(dataset[\"hdl\"].values.reshape(403,1))\n","dataset[\"ratio\"] = sc.fit_transform(dataset[\"ratio\"].values.reshape(403,1))\n","dataset['waist'] = sc.fit_transform(dataset[\"waist\"].values.reshape(403,1))\n","dataset[\"weight\"] = sc.fit_transform(dataset[\"weight\"].values.reshape(403,1))\n","dataset[\"chol\"] = sc.fit_transform(dataset[\"chol\"].values.reshape(403,1))\n","dataset[\"bp.1s\"] = sc.fit_transform(dataset[\"bp.1s\"].values.reshape(403,1))\n","dataset[\"bp.1d\"] = sc.fit_transform(dataset[\"bp.1d\"].values.reshape(403,1))\n","dataset[\"time.ppn\"] = sc.fit_transform(dataset[\"time.ppn\"].values.reshape(403,1))\n","dataset[\"hip\"] = sc.fit_transform(dataset[\"hip\"].values.reshape(403,1))\n","dataset[\"age\"] = sc.fit_transform(dataset[\"age\"].values.reshape(403,1))\n","dataset[\"height\"] = sc.fit_transform(dataset[\"height\"].values.reshape(403,1))"],"execution_count":9,"outputs":[]},{"cell_type":"code","metadata":{"id":"mJ9GhIXfW-gF","executionInfo":{"status":"ok","timestamp":1625491913794,"user_tz":-330,"elapsed":9,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["# Creating Y \n","y = dataset[\"glyhb\"]\n","dataset.drop(columns=\"glyhb\",inplace=True)"],"execution_count":10,"outputs":[]},{"cell_type":"code","metadata":{"id":"jGj7D50tW-gv","executionInfo":{"status":"ok","timestamp":1625491913795,"user_tz":-330,"elapsed":9,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["## Metric Table Function\n","from sklearn.metrics import r2_score,mean_squared_error,mean_absolute_error\n","from prettytable import PrettyTable\n","\n","def metrics(y_test,y_pred):\n","    r2score = r2_score(y_test,y_pred)\n","    MAD = np.mean(np.abs(y_pred-np.mean(y_test)))\n","    MAE = mean_absolute_error(y_test,y_pred)\n","    RMSE = np.sqrt(mean_squared_error(y_test,y_pred))\n","    MSE=mean_squared_error(y_test,y_pred)\n","    t = PrettyTable(['Error Metric', 'Value'])\n","    t.add_row([\"r2_score\",r2score])\n","    t.add_row([\"MSE\",MSE])\n","    t.add_row(['MAE', MAE])\n","    t.add_row([\"RMSE\",RMSE,])\n","    t.add_row([\"MAD\",MAD])\n","    return t,r2score,MAD,MAE,RMSE,MSE"],"execution_count":11,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"A5cZaRs-Pcvl"},"source":["## Main Loop for N Runs from Here:"]},{"cell_type":"markdown","metadata":{"id":"J8VFwWEWW-gF"},"source":["### Splitting train and test values"]},{"cell_type":"code","metadata":{"id":"qk2PWQO2W-gw","executionInfo":{"status":"ok","timestamp":1625491914441,"user_tz":-330,"elapsed":654,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["# Imports\n","from sklearn.model_selection import train_test_split\n","from sklearn.preprocessing import LabelEncoder\n","from sklearn.preprocessing import OneHotEncoder\n","\n","from sklearn.linear_model import Ridge\n","from sklearn.model_selection import GridSearchCV\n","from sklearn.ensemble import RandomForestRegressor\n","from sklearn.linear_model import Lasso\n","import xgboost as xgb\n","from xgboost.sklearn import XGBRegressor\n","from scipy.optimize import minimize\n","from tqdm import tqdm"],"execution_count":12,"outputs":[]},{"cell_type":"code","metadata":{"id":"VIWE0vjXkBRQ","executionInfo":{"status":"ok","timestamp":1625491914442,"user_tz":-330,"elapsed":6,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["n = 10\n","# Lets create a table for storing data \n","\n","df = pd.DataFrame(columns=[\"RunNo\",\"Model\",\"R2score\",\"MSE\",\"MAE\",\"MAD\",\"RMSE\"])\n","\n","# Data for storing the weights\n","df_weights = pd.DataFrame(columns = [\"RunNo\",\"Ridge\",\"Random Forest\",\"Lasso\",\"XGBREGRESSOR\"])"],"execution_count":13,"outputs":[]},{"cell_type":"code","metadata":{"id":"yDuzbhnmW-gG","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1625492638423,"user_tz":-330,"elapsed":723986,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"c82e08b9-596c-4814-e197-0c0e206e3184"},"source":["for i in tqdm(range(n), desc='Mulitple Run Progress'):\n","  print()\n","  print(\"Run Number \",i+1)\n","  x_train,x_test,y_train,y_test = train_test_split(dataset,y,test_size=0.2)\n","  le = LabelEncoder()\n","  combine = x_train.append(x_test)\n","  combine[\"location\"] = le.fit_transform(combine[\"location\"])\n","  combine[\"gender\"] = le.fit_transform(combine[\"gender\"])\n","  combine[\"frame\"] = le.fit_transform(combine[\"frame\"])\n","  combine = pd.concat([combine,pd.get_dummies(combine[\"frame\"])],axis=1)\n","  combine.drop(columns=\"frame\",inplace=True)\n","  x_train = combine.iloc[:322]\n","  x_test = combine.iloc[322:]\n","\n","  ## Machine Learning\n","\n","  ## Ridge\n","  ridge_reg = Ridge()\n","  params_Ridge = {'alpha': [1,0.1,0.01,0.001,0.0001,0] , \"fit_intercept\": [True, False], \"solver\": ['svd', 'cholesky', 'lsqr', 'sparse_cg', 'sag', 'saga']}\n","  Ridge_GS = GridSearchCV(ridge_reg, param_grid=params_Ridge, n_jobs=-1, cv=10)\n","  Ridge_GS.fit(x_train,y_train)\n","  Ridge_best_model = Ridge_GS.best_estimator_\n","  Ridge_best_model.fit(x_train,y_train)\n","  y_Ridge_GS_pred= Ridge_best_model.predict(x_test)\n","  t,r2score,MAD,MAE,RMSE,MSE = metrics(y_test,y_Ridge_GS_pred)\n","  df.loc[len(df.index)] = [i+1,\"Ridge\",r2score,MSE,MAE,MAD,RMSE]\n","\n","\n","  ## Random Forest\n","  rf = RandomForestRegressor(n_estimators=20,\n","      max_depth=2,\n","      min_samples_split=2,\n","      min_samples_leaf=1,)\n","  rf.fit(x_train,y_train)\n","  y_rf = rf.predict(x_test)\n","  t,r2score,MAD,MAE,RMSE,MSE = metrics(y_test,y_rf)\n","  df.loc[len(df.index)] = [i+1,\"Random Forest\",r2score,MSE,MAE,MAD,RMSE]\n","\n","\n","  ## lasso\n","  lasso_reg = Lasso()\n","  params_lasso = {'alpha':[0.02, 0.024, 0.025, 0.026, 0.03] , \"fit_intercept\": [True, False]}\n","  lasso_GS = GridSearchCV(lasso_reg, param_grid=params_lasso, n_jobs=-1,cv=10)\n","  lasso_GS.fit(x_train,y_train)\n","  Lasso_best_model = lasso_GS.best_estimator_\n","  Lasso_best_model.fit(x_train,y_train)\n","  y_lasso_GS_pred= Lasso_best_model.predict(x_test)\n","  t,r2score,MAD,MAE,RMSE,MSE = metrics(y_test,y_lasso_GS_pred)\n","  df.loc[len(df.index)] = [i+1,\"Lasso\",r2score,MSE,MAE,MAD,RMSE]\n","\n","\n","  ## XGBRegressor\n","\n","  xgb1 = XGBRegressor()\n","  parameters = {'nthread':[4], \n","                'objective':['reg:linear'],\n","                'learning_rate': [.03, 0.05, .07],\n","                'max_depth': [5, 6, 7],\n","                'min_child_weight': [4],\n","                'silent': [1],\n","                'subsample': [0.7],\n","                'colsample_bytree': [0.7],\n","                'n_estimators': [500]}\n","\n","  xgb_grid = GridSearchCV(xgb1,parameters,cv = 10,n_jobs = 5)\n","  xgb_grid.fit(x_train,y_train)\n","  xgb_best_model = xgb_grid.best_estimator_\n","  xgb_best_model.fit(x_train,y_train)\n","  y_XGBReg_pred= xgb_best_model.predict(x_test)\n","  #print(metrics(y_test,y_XGBReg_pred))\n","  t,r2score,MAD,MAE,RMSE,MSE = metrics(y_test,y_XGBReg_pred)\n","  df.loc[len(df.index)] = [i+1,\"XGBRegressor\",r2score,MSE,MAE,MAD,RMSE]\n","\n","  ## Ensemble Learning with Average weights\n","  Ensemble_average_prediction_1 = ( y_XGBReg_pred+ y_lasso_GS_pred+ y_rf + y_Ridge_GS_pred ) / 4\n","  #print(metrics(y_test,Ensemble_average_prediction_1))\n","  t,r2score,MAD,MAE,RMSE,MSE = metrics(y_test,Ensemble_average_prediction_1)\n","  df.loc[len(df.index)] = [i+1,\"Ensemble Avg Weight\",r2score,MSE,MAE,MAD,RMSE]\n","\n","\n","  ## Ensemble Learning with Optimized Weights\n","  rmse_optimize =[]\n","  def rmse_loss_func(weights):\n","      ''' scipy minimize will pass the weights as a numpy array '''\n","      final_prediction = 0\n","      for weight, prediction in zip(weights, predictions):\n","              final_prediction += weight*prediction\n","\n","      #print(np.sqrt(mean_squared_error(y_test,final_prediction)),weights)\n","      rmse_optimize.append(np.sqrt(mean_squared_error(y_test,final_prediction)))\n","      return np.sqrt(mean_squared_error(y_test,final_prediction))\n","  # add every model's prediction into list\n","  predictions = []\n","  predictions.append(y_Ridge_GS_pred)\n","  predictions.append(y_rf)\n","  predictions.append(y_lasso_GS_pred)\n","  predictions.append(y_XGBReg_pred)\n","  starting_values = [0.5]*len(predictions)\n","  res = minimize(rmse_loss_func, starting_values, method='Powell')\n","  best_weights=res[\"x\"]\n","  w1,w2,w3,w4 = best_weights[0],best_weights[1],best_weights[2],best_weights[3]\n","  df_weights.loc[len(df_weights.index)] = [i+1,w1,w2,w3,w4]\n","  Ensemble_average_prediction_2 = ( y_XGBReg_pred*w4+ y_lasso_GS_pred*w3 + y_rf*w2 +\n","                                  y_Ridge_GS_pred*w1)\n","  \n","  \n","  t,r2score,MAD,MAE,RMSE,MSE = metrics(y_test,Ensemble_average_prediction_2)\n","  print(t)\n","  df.loc[len(df.index)] = [i+1,\"Ensemble Optimized Weight\",r2score,MSE,MAE,MAD,RMSE]\n","  print(\"-----------------------------------------------------------------------\")\n"],"execution_count":14,"outputs":[{"output_type":"stream","text":["\rMulitple Run Progress:   0%|          | 0/10 [00:00<?, ?it/s]"],"name":"stderr"},{"output_type":"stream","text":["\n","Run Number  1\n"],"name":"stdout"},{"output_type":"stream","text":["\rMulitple Run Progress:  10%|█         | 1/10 [01:09<10:24, 69.38s/it]"],"name":"stderr"},{"output_type":"stream","text":["+--------------+--------------------+\n","| Error Metric |       Value        |\n","+--------------+--------------------+\n","|   r2_score   | 0.6909916446121267 |\n","|     MSE      | 1.8356891831890074 |\n","|     MAE      | 0.9720630777193173 |\n","|     RMSE     | 1.3548760766907826 |\n","|     MAD      | 1.260273209074893  |\n","+--------------+--------------------+\n","-----------------------------------------------------------------------\n","\n","Run Number  2\n"],"name":"stdout"},{"output_type":"stream","text":["\rMulitple Run Progress:  20%|██        | 2/10 [02:18<09:14, 69.34s/it]"],"name":"stderr"},{"output_type":"stream","text":["+--------------+---------------------+\n","| Error Metric |        Value        |\n","+--------------+---------------------+\n","|   r2_score   | 0.37541460405604876 |\n","|     MSE      |  2.1614157431860255 |\n","|     MAE      |  0.8217977814253825 |\n","|     RMSE     |  1.4701754123865716 |\n","|     MAD      |  0.8306501827480853 |\n","+--------------+---------------------+\n","-----------------------------------------------------------------------\n","\n","Run Number  3\n"],"name":"stdout"},{"output_type":"stream","text":["\rMulitple Run Progress:  30%|███       | 3/10 [03:27<08:03, 69.14s/it]"],"name":"stderr"},{"output_type":"stream","text":["+--------------+--------------------+\n","| Error Metric |       Value        |\n","+--------------+--------------------+\n","|   r2_score   | 0.1374670682228496 |\n","|     MSE      | 1.6588317928330159 |\n","|     MAE      | 0.7569697574386631 |\n","|     RMSE     | 1.2879564405805872 |\n","|     MAD      | 0.9336728758376027 |\n","+--------------+--------------------+\n","-----------------------------------------------------------------------\n","\n","Run Number  4\n"],"name":"stdout"},{"output_type":"stream","text":["\rMulitple Run Progress:  40%|████      | 4/10 [04:35<06:52, 68.82s/it]"],"name":"stderr"},{"output_type":"stream","text":["+--------------+--------------------+\n","| Error Metric |       Value        |\n","+--------------+--------------------+\n","|   r2_score   | 0.6487094759860006 |\n","|     MSE      | 2.0531136022076812 |\n","|     MAE      | 1.0152665154654992 |\n","|     RMSE     | 1.4328690108337472 |\n","|     MAD      | 1.111416424753916  |\n","+--------------+--------------------+\n","-----------------------------------------------------------------------\n","\n","Run Number  5\n"],"name":"stdout"},{"output_type":"stream","text":["\rMulitple Run Progress:  50%|█████     | 5/10 [05:44<05:44, 68.96s/it]"],"name":"stderr"},{"output_type":"stream","text":["+--------------+--------------------+\n","| Error Metric |       Value        |\n","+--------------+--------------------+\n","|   r2_score   | 0.5557587102849417 |\n","|     MSE      | 2.075172767330966  |\n","|     MAE      | 0.8182972339577167 |\n","|     RMSE     | 1.4405459962566158 |\n","|     MAD      | 0.9185684155935386 |\n","+--------------+--------------------+\n","-----------------------------------------------------------------------\n","\n","Run Number  6\n"],"name":"stdout"},{"output_type":"stream","text":["\rMulitple Run Progress:  60%|██████    | 6/10 [06:52<04:34, 68.58s/it]"],"name":"stderr"},{"output_type":"stream","text":["+--------------+--------------------+\n","| Error Metric |       Value        |\n","+--------------+--------------------+\n","|   r2_score   | 0.522991368249033  |\n","|     MSE      | 2.1501661878362675 |\n","|     MAE      | 0.9522985021812517 |\n","|     RMSE     | 1.4663444983482794 |\n","|     MAD      | 1.4653170973986254 |\n","+--------------+--------------------+\n","-----------------------------------------------------------------------\n","\n","Run Number  7\n"],"name":"stdout"},{"output_type":"stream","text":["\rMulitple Run Progress:  70%|███████   | 7/10 [08:04<03:29, 69.67s/it]"],"name":"stderr"},{"output_type":"stream","text":["+--------------+--------------------+\n","| Error Metric |       Value        |\n","+--------------+--------------------+\n","|   r2_score   | 0.7242923922955378 |\n","|     MSE      | 1.6493439897729114 |\n","|     MAE      | 0.919799490824033  |\n","|     RMSE     | 1.284267880846092  |\n","|     MAD      | 1.2308467700088417 |\n","+--------------+--------------------+\n","-----------------------------------------------------------------------\n","\n","Run Number  8\n"],"name":"stdout"},{"output_type":"stream","text":["\rMulitple Run Progress:  80%|████████  | 8/10 [09:14<02:19, 69.65s/it]"],"name":"stderr"},{"output_type":"stream","text":["+--------------+--------------------+\n","| Error Metric |       Value        |\n","+--------------+--------------------+\n","|   r2_score   | 0.6819931142522496 |\n","|     MSE      | 1.7143205445212828 |\n","|     MAE      | 0.8980917929156852 |\n","|     RMSE     | 1.3093206423643076 |\n","|     MAD      | 0.9511742326294538 |\n","+--------------+--------------------+\n","-----------------------------------------------------------------------\n","\n","Run Number  9\n"],"name":"stdout"},{"output_type":"stream","text":["\rMulitple Run Progress:  90%|█████████ | 9/10 [10:43<01:15, 75.65s/it]"],"name":"stderr"},{"output_type":"stream","text":["+--------------+--------------------+\n","| Error Metric |       Value        |\n","+--------------+--------------------+\n","|   r2_score   | 0.5542198125652789 |\n","|     MSE      |  1.84302635337017  |\n","|     MAE      | 0.8648062290368794 |\n","|     RMSE     | 1.3575810669607065 |\n","|     MAD      | 1.2779095337901016 |\n","+--------------+--------------------+\n","-----------------------------------------------------------------------\n","\n","Run Number  10\n"],"name":"stdout"},{"output_type":"stream","text":["Mulitple Run Progress: 100%|██████████| 10/10 [12:03<00:00, 72.39s/it]"],"name":"stderr"},{"output_type":"stream","text":["+--------------+--------------------+\n","| Error Metric |       Value        |\n","+--------------+--------------------+\n","|   r2_score   | 0.6276937744181736 |\n","|     MSE      | 1.9699447986413747 |\n","|     MAE      | 0.7431554473084505 |\n","|     RMSE     | 1.4035472199542753 |\n","|     MAD      | 1.184959400270358  |\n","+--------------+--------------------+\n","-----------------------------------------------------------------------\n"],"name":"stdout"},{"output_type":"stream","text":["\n"],"name":"stderr"}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"FO3F9dqY7KiE","executionInfo":{"status":"ok","timestamp":1625492863974,"user_tz":-330,"elapsed":661,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"0b1a45dc-2057-4ef7-9c28-ef13342e132a"},"source":["df"],"execution_count":15,"outputs":[{"output_type":"execute_result","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>RunNo</th>\n","      <th>Model</th>\n","      <th>R2score</th>\n","      <th>MSE</th>\n","      <th>MAE</th>\n","      <th>MAD</th>\n","      <th>RMSE</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>1</td>\n","      <td>Ridge</td>\n","      <td>0.644507</td>\n","      <td>2.111834</td>\n","      <td>1.067321</td>\n","      <td>1.275773</td>\n","      <td>1.453215</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>1</td>\n","      <td>Random Forest</td>\n","      <td>0.632643</td>\n","      <td>2.182311</td>\n","      <td>0.996266</td>\n","      <td>1.320672</td>\n","      <td>1.477265</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>1</td>\n","      <td>Lasso</td>\n","      <td>0.656784</td>\n","      <td>2.038905</td>\n","      <td>1.045599</td>\n","      <td>1.273856</td>\n","      <td>1.427902</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>1</td>\n","      <td>XGBRegressor</td>\n","      <td>0.519800</td>\n","      <td>2.852667</td>\n","      <td>1.182715</td>\n","      <td>1.442239</td>\n","      <td>1.688984</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>1</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.639209</td>\n","      <td>2.143309</td>\n","      <td>1.035871</td>\n","      <td>1.298237</td>\n","      <td>1.464004</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>1</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.690992</td>\n","      <td>1.835689</td>\n","      <td>0.972063</td>\n","      <td>1.260273</td>\n","      <td>1.354876</td>\n","    </tr>\n","    <tr>\n","      <th>6</th>\n","      <td>2</td>\n","      <td>Ridge</td>\n","      <td>0.333930</td>\n","      <td>2.304975</td>\n","      <td>0.899566</td>\n","      <td>0.889502</td>\n","      <td>1.518214</td>\n","    </tr>\n","    <tr>\n","      <th>7</th>\n","      <td>2</td>\n","      <td>Random Forest</td>\n","      <td>0.282435</td>\n","      <td>2.483177</td>\n","      <td>0.864953</td>\n","      <td>0.725376</td>\n","      <td>1.575810</td>\n","    </tr>\n","    <tr>\n","      <th>8</th>\n","      <td>2</td>\n","      <td>Lasso</td>\n","      <td>0.362552</td>\n","      <td>2.205929</td>\n","      <td>0.871122</td>\n","      <td>0.844700</td>\n","      <td>1.485237</td>\n","    </tr>\n","    <tr>\n","      <th>9</th>\n","      <td>2</td>\n","      <td>XGBRegressor</td>\n","      <td>0.293766</td>\n","      <td>2.443967</td>\n","      <td>0.895849</td>\n","      <td>0.832135</td>\n","      <td>1.563319</td>\n","    </tr>\n","    <tr>\n","      <th>10</th>\n","      <td>2</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.352557</td>\n","      <td>2.240514</td>\n","      <td>0.826319</td>\n","      <td>0.772871</td>\n","      <td>1.496835</td>\n","    </tr>\n","    <tr>\n","      <th>11</th>\n","      <td>2</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.375415</td>\n","      <td>2.161416</td>\n","      <td>0.821798</td>\n","      <td>0.830650</td>\n","      <td>1.470175</td>\n","    </tr>\n","    <tr>\n","      <th>12</th>\n","      <td>3</td>\n","      <td>Ridge</td>\n","      <td>-0.100393</td>\n","      <td>2.116287</td>\n","      <td>0.879393</td>\n","      <td>0.941284</td>\n","      <td>1.454746</td>\n","    </tr>\n","    <tr>\n","      <th>13</th>\n","      <td>3</td>\n","      <td>Random Forest</td>\n","      <td>0.006756</td>\n","      <td>1.910217</td>\n","      <td>0.799853</td>\n","      <td>0.814188</td>\n","      <td>1.382106</td>\n","    </tr>\n","    <tr>\n","      <th>14</th>\n","      <td>3</td>\n","      <td>Lasso</td>\n","      <td>-0.033642</td>\n","      <td>1.987910</td>\n","      <td>0.861939</td>\n","      <td>0.896527</td>\n","      <td>1.409933</td>\n","    </tr>\n","    <tr>\n","      <th>15</th>\n","      <td>3</td>\n","      <td>XGBRegressor</td>\n","      <td>0.012948</td>\n","      <td>1.898309</td>\n","      <td>0.886497</td>\n","      <td>0.986811</td>\n","      <td>1.377791</td>\n","    </tr>\n","    <tr>\n","      <th>16</th>\n","      <td>3</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.031660</td>\n","      <td>1.862321</td>\n","      <td>0.818363</td>\n","      <td>0.879041</td>\n","      <td>1.364669</td>\n","    </tr>\n","    <tr>\n","      <th>17</th>\n","      <td>3</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.137467</td>\n","      <td>1.658832</td>\n","      <td>0.756970</td>\n","      <td>0.933673</td>\n","      <td>1.287956</td>\n","    </tr>\n","    <tr>\n","      <th>18</th>\n","      <td>4</td>\n","      <td>Ridge</td>\n","      <td>0.566320</td>\n","      <td>2.534640</td>\n","      <td>1.132670</td>\n","      <td>1.224636</td>\n","      <td>1.592055</td>\n","    </tr>\n","    <tr>\n","      <th>19</th>\n","      <td>4</td>\n","      <td>Random Forest</td>\n","      <td>0.636206</td>\n","      <td>2.126191</td>\n","      <td>0.989122</td>\n","      <td>1.175443</td>\n","      <td>1.458146</td>\n","    </tr>\n","    <tr>\n","      <th>20</th>\n","      <td>4</td>\n","      <td>Lasso</td>\n","      <td>0.594680</td>\n","      <td>2.368886</td>\n","      <td>1.096253</td>\n","      <td>1.212077</td>\n","      <td>1.539118</td>\n","    </tr>\n","    <tr>\n","      <th>21</th>\n","      <td>4</td>\n","      <td>XGBRegressor</td>\n","      <td>0.536173</td>\n","      <td>2.710833</td>\n","      <td>1.171004</td>\n","      <td>1.200118</td>\n","      <td>1.646461</td>\n","    </tr>\n","    <tr>\n","      <th>22</th>\n","      <td>4</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.613520</td>\n","      <td>2.258778</td>\n","      <td>1.033659</td>\n","      <td>1.158617</td>\n","      <td>1.502923</td>\n","    </tr>\n","    <tr>\n","      <th>23</th>\n","      <td>4</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.648709</td>\n","      <td>2.053114</td>\n","      <td>1.015267</td>\n","      <td>1.111416</td>\n","      <td>1.432869</td>\n","    </tr>\n","    <tr>\n","      <th>24</th>\n","      <td>5</td>\n","      <td>Ridge</td>\n","      <td>0.479061</td>\n","      <td>2.433446</td>\n","      <td>0.954529</td>\n","      <td>1.107036</td>\n","      <td>1.559951</td>\n","    </tr>\n","    <tr>\n","      <th>25</th>\n","      <td>5</td>\n","      <td>Random Forest</td>\n","      <td>0.517291</td>\n","      <td>2.254867</td>\n","      <td>0.834138</td>\n","      <td>0.993075</td>\n","      <td>1.501621</td>\n","    </tr>\n","    <tr>\n","      <th>26</th>\n","      <td>5</td>\n","      <td>Lasso</td>\n","      <td>0.493389</td>\n","      <td>2.366517</td>\n","      <td>0.940848</td>\n","      <td>1.090959</td>\n","      <td>1.538349</td>\n","    </tr>\n","    <tr>\n","      <th>27</th>\n","      <td>5</td>\n","      <td>XGBRegressor</td>\n","      <td>0.493315</td>\n","      <td>2.366864</td>\n","      <td>0.851092</td>\n","      <td>1.021348</td>\n","      <td>1.538462</td>\n","    </tr>\n","    <tr>\n","      <th>28</th>\n","      <td>5</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.534960</td>\n","      <td>2.172327</td>\n","      <td>0.821111</td>\n","      <td>1.027603</td>\n","      <td>1.473882</td>\n","    </tr>\n","    <tr>\n","      <th>29</th>\n","      <td>5</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.555759</td>\n","      <td>2.075173</td>\n","      <td>0.818297</td>\n","      <td>0.918568</td>\n","      <td>1.440546</td>\n","    </tr>\n","    <tr>\n","      <th>30</th>\n","      <td>6</td>\n","      <td>Ridge</td>\n","      <td>0.430987</td>\n","      <td>2.564885</td>\n","      <td>1.042361</td>\n","      <td>1.530750</td>\n","      <td>1.601526</td>\n","    </tr>\n","    <tr>\n","      <th>31</th>\n","      <td>6</td>\n","      <td>Random Forest</td>\n","      <td>0.508856</td>\n","      <td>2.213882</td>\n","      <td>0.978219</td>\n","      <td>1.439189</td>\n","      <td>1.487912</td>\n","    </tr>\n","    <tr>\n","      <th>32</th>\n","      <td>6</td>\n","      <td>Lasso</td>\n","      <td>0.452711</td>\n","      <td>2.466961</td>\n","      <td>1.047269</td>\n","      <td>1.480934</td>\n","      <td>1.570656</td>\n","    </tr>\n","    <tr>\n","      <th>33</th>\n","      <td>6</td>\n","      <td>XGBRegressor</td>\n","      <td>0.462935</td>\n","      <td>2.420876</td>\n","      <td>1.025272</td>\n","      <td>1.493245</td>\n","      <td>1.555916</td>\n","    </tr>\n","    <tr>\n","      <th>34</th>\n","      <td>6</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.504195</td>\n","      <td>2.234892</td>\n","      <td>0.956090</td>\n","      <td>1.471994</td>\n","      <td>1.494955</td>\n","    </tr>\n","    <tr>\n","      <th>35</th>\n","      <td>6</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.522991</td>\n","      <td>2.150166</td>\n","      <td>0.952299</td>\n","      <td>1.465317</td>\n","      <td>1.466344</td>\n","    </tr>\n","    <tr>\n","      <th>36</th>\n","      <td>7</td>\n","      <td>Ridge</td>\n","      <td>0.655392</td>\n","      <td>2.061523</td>\n","      <td>1.002330</td>\n","      <td>1.234028</td>\n","      <td>1.435800</td>\n","    </tr>\n","    <tr>\n","      <th>37</th>\n","      <td>7</td>\n","      <td>Random Forest</td>\n","      <td>0.683232</td>\n","      <td>1.894978</td>\n","      <td>0.929851</td>\n","      <td>1.330725</td>\n","      <td>1.376582</td>\n","    </tr>\n","    <tr>\n","      <th>38</th>\n","      <td>7</td>\n","      <td>Lasso</td>\n","      <td>0.700638</td>\n","      <td>1.790850</td>\n","      <td>0.960784</td>\n","      <td>1.174809</td>\n","      <td>1.338226</td>\n","    </tr>\n","    <tr>\n","      <th>39</th>\n","      <td>7</td>\n","      <td>XGBRegressor</td>\n","      <td>0.604689</td>\n","      <td>2.364835</td>\n","      <td>1.038795</td>\n","      <td>1.379540</td>\n","      <td>1.537802</td>\n","    </tr>\n","    <tr>\n","      <th>40</th>\n","      <td>7</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.685014</td>\n","      <td>1.884315</td>\n","      <td>0.943481</td>\n","      <td>1.247478</td>\n","      <td>1.372704</td>\n","    </tr>\n","    <tr>\n","      <th>41</th>\n","      <td>7</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.724292</td>\n","      <td>1.649344</td>\n","      <td>0.919799</td>\n","      <td>1.230847</td>\n","      <td>1.284268</td>\n","    </tr>\n","    <tr>\n","      <th>42</th>\n","      <td>8</td>\n","      <td>Ridge</td>\n","      <td>0.621631</td>\n","      <td>2.039720</td>\n","      <td>1.066954</td>\n","      <td>0.942742</td>\n","      <td>1.428188</td>\n","    </tr>\n","    <tr>\n","      <th>43</th>\n","      <td>8</td>\n","      <td>Random Forest</td>\n","      <td>0.670064</td>\n","      <td>1.778628</td>\n","      <td>0.892719</td>\n","      <td>0.946690</td>\n","      <td>1.333652</td>\n","    </tr>\n","    <tr>\n","      <th>44</th>\n","      <td>8</td>\n","      <td>Lasso</td>\n","      <td>0.642278</td>\n","      <td>1.928419</td>\n","      <td>1.028936</td>\n","      <td>0.957245</td>\n","      <td>1.388675</td>\n","    </tr>\n","    <tr>\n","      <th>45</th>\n","      <td>8</td>\n","      <td>XGBRegressor</td>\n","      <td>0.625442</td>\n","      <td>2.019179</td>\n","      <td>1.030408</td>\n","      <td>1.067537</td>\n","      <td>1.420978</td>\n","    </tr>\n","    <tr>\n","      <th>46</th>\n","      <td>8</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.664281</td>\n","      <td>1.809803</td>\n","      <td>0.969416</td>\n","      <td>0.930193</td>\n","      <td>1.345289</td>\n","    </tr>\n","    <tr>\n","      <th>47</th>\n","      <td>8</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.681993</td>\n","      <td>1.714321</td>\n","      <td>0.898092</td>\n","      <td>0.951174</td>\n","      <td>1.309321</td>\n","    </tr>\n","    <tr>\n","      <th>48</th>\n","      <td>9</td>\n","      <td>Ridge</td>\n","      <td>0.469439</td>\n","      <td>2.193544</td>\n","      <td>1.012066</td>\n","      <td>1.299021</td>\n","      <td>1.481062</td>\n","    </tr>\n","    <tr>\n","      <th>49</th>\n","      <td>9</td>\n","      <td>Random Forest</td>\n","      <td>0.479735</td>\n","      <td>2.150974</td>\n","      <td>1.010538</td>\n","      <td>1.254897</td>\n","      <td>1.466620</td>\n","    </tr>\n","    <tr>\n","      <th>50</th>\n","      <td>9</td>\n","      <td>Lasso</td>\n","      <td>0.494972</td>\n","      <td>2.087981</td>\n","      <td>1.000324</td>\n","      <td>1.251222</td>\n","      <td>1.444985</td>\n","    </tr>\n","    <tr>\n","      <th>51</th>\n","      <td>9</td>\n","      <td>XGBRegressor</td>\n","      <td>0.475003</td>\n","      <td>2.170541</td>\n","      <td>1.037057</td>\n","      <td>1.227199</td>\n","      <td>1.473276</td>\n","    </tr>\n","    <tr>\n","      <th>52</th>\n","      <td>9</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.526299</td>\n","      <td>1.958464</td>\n","      <td>0.936504</td>\n","      <td>1.224674</td>\n","      <td>1.399451</td>\n","    </tr>\n","    <tr>\n","      <th>53</th>\n","      <td>9</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.554220</td>\n","      <td>1.843026</td>\n","      <td>0.864806</td>\n","      <td>1.277910</td>\n","      <td>1.357581</td>\n","    </tr>\n","    <tr>\n","      <th>54</th>\n","      <td>10</td>\n","      <td>Ridge</td>\n","      <td>0.572203</td>\n","      <td>2.263559</td>\n","      <td>0.893557</td>\n","      <td>1.215844</td>\n","      <td>1.504513</td>\n","    </tr>\n","    <tr>\n","      <th>55</th>\n","      <td>10</td>\n","      <td>Random Forest</td>\n","      <td>0.616028</td>\n","      <td>2.031671</td>\n","      <td>0.750408</td>\n","      <td>1.191850</td>\n","      <td>1.425367</td>\n","    </tr>\n","    <tr>\n","      <th>56</th>\n","      <td>10</td>\n","      <td>Lasso</td>\n","      <td>0.590688</td>\n","      <td>2.165752</td>\n","      <td>0.864556</td>\n","      <td>1.227404</td>\n","      <td>1.471649</td>\n","    </tr>\n","    <tr>\n","      <th>57</th>\n","      <td>10</td>\n","      <td>XGBRegressor</td>\n","      <td>0.545758</td>\n","      <td>2.403482</td>\n","      <td>0.839365</td>\n","      <td>1.339924</td>\n","      <td>1.550317</td>\n","    </tr>\n","    <tr>\n","      <th>58</th>\n","      <td>10</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.613084</td>\n","      <td>2.047247</td>\n","      <td>0.760479</td>\n","      <td>1.204986</td>\n","      <td>1.430820</td>\n","    </tr>\n","    <tr>\n","      <th>59</th>\n","      <td>10</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.627694</td>\n","      <td>1.969945</td>\n","      <td>0.743155</td>\n","      <td>1.184959</td>\n","      <td>1.403547</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["   RunNo                      Model   R2score  ...       MAE       MAD      RMSE\n","0      1                      Ridge  0.644507  ...  1.067321  1.275773  1.453215\n","1      1              Random Forest  0.632643  ...  0.996266  1.320672  1.477265\n","2      1                      Lasso  0.656784  ...  1.045599  1.273856  1.427902\n","3      1               XGBRegressor  0.519800  ...  1.182715  1.442239  1.688984\n","4      1        Ensemble Avg Weight  0.639209  ...  1.035871  1.298237  1.464004\n","5      1  Ensemble Optimized Weight  0.690992  ...  0.972063  1.260273  1.354876\n","6      2                      Ridge  0.333930  ...  0.899566  0.889502  1.518214\n","7      2              Random Forest  0.282435  ...  0.864953  0.725376  1.575810\n","8      2                      Lasso  0.362552  ...  0.871122  0.844700  1.485237\n","9      2               XGBRegressor  0.293766  ...  0.895849  0.832135  1.563319\n","10     2        Ensemble Avg Weight  0.352557  ...  0.826319  0.772871  1.496835\n","11     2  Ensemble Optimized Weight  0.375415  ...  0.821798  0.830650  1.470175\n","12     3                      Ridge -0.100393  ...  0.879393  0.941284  1.454746\n","13     3              Random Forest  0.006756  ...  0.799853  0.814188  1.382106\n","14     3                      Lasso -0.033642  ...  0.861939  0.896527  1.409933\n","15     3               XGBRegressor  0.012948  ...  0.886497  0.986811  1.377791\n","16     3        Ensemble Avg Weight  0.031660  ...  0.818363  0.879041  1.364669\n","17     3  Ensemble Optimized Weight  0.137467  ...  0.756970  0.933673  1.287956\n","18     4                      Ridge  0.566320  ...  1.132670  1.224636  1.592055\n","19     4              Random Forest  0.636206  ...  0.989122  1.175443  1.458146\n","20     4                      Lasso  0.594680  ...  1.096253  1.212077  1.539118\n","21     4               XGBRegressor  0.536173  ...  1.171004  1.200118  1.646461\n","22     4        Ensemble Avg Weight  0.613520  ...  1.033659  1.158617  1.502923\n","23     4  Ensemble Optimized Weight  0.648709  ...  1.015267  1.111416  1.432869\n","24     5                      Ridge  0.479061  ...  0.954529  1.107036  1.559951\n","25     5              Random Forest  0.517291  ...  0.834138  0.993075  1.501621\n","26     5                      Lasso  0.493389  ...  0.940848  1.090959  1.538349\n","27     5               XGBRegressor  0.493315  ...  0.851092  1.021348  1.538462\n","28     5        Ensemble Avg Weight  0.534960  ...  0.821111  1.027603  1.473882\n","29     5  Ensemble Optimized Weight  0.555759  ...  0.818297  0.918568  1.440546\n","30     6                      Ridge  0.430987  ...  1.042361  1.530750  1.601526\n","31     6              Random Forest  0.508856  ...  0.978219  1.439189  1.487912\n","32     6                      Lasso  0.452711  ...  1.047269  1.480934  1.570656\n","33     6               XGBRegressor  0.462935  ...  1.025272  1.493245  1.555916\n","34     6        Ensemble Avg Weight  0.504195  ...  0.956090  1.471994  1.494955\n","35     6  Ensemble Optimized Weight  0.522991  ...  0.952299  1.465317  1.466344\n","36     7                      Ridge  0.655392  ...  1.002330  1.234028  1.435800\n","37     7              Random Forest  0.683232  ...  0.929851  1.330725  1.376582\n","38     7                      Lasso  0.700638  ...  0.960784  1.174809  1.338226\n","39     7               XGBRegressor  0.604689  ...  1.038795  1.379540  1.537802\n","40     7        Ensemble Avg Weight  0.685014  ...  0.943481  1.247478  1.372704\n","41     7  Ensemble Optimized Weight  0.724292  ...  0.919799  1.230847  1.284268\n","42     8                      Ridge  0.621631  ...  1.066954  0.942742  1.428188\n","43     8              Random Forest  0.670064  ...  0.892719  0.946690  1.333652\n","44     8                      Lasso  0.642278  ...  1.028936  0.957245  1.388675\n","45     8               XGBRegressor  0.625442  ...  1.030408  1.067537  1.420978\n","46     8        Ensemble Avg Weight  0.664281  ...  0.969416  0.930193  1.345289\n","47     8  Ensemble Optimized Weight  0.681993  ...  0.898092  0.951174  1.309321\n","48     9                      Ridge  0.469439  ...  1.012066  1.299021  1.481062\n","49     9              Random Forest  0.479735  ...  1.010538  1.254897  1.466620\n","50     9                      Lasso  0.494972  ...  1.000324  1.251222  1.444985\n","51     9               XGBRegressor  0.475003  ...  1.037057  1.227199  1.473276\n","52     9        Ensemble Avg Weight  0.526299  ...  0.936504  1.224674  1.399451\n","53     9  Ensemble Optimized Weight  0.554220  ...  0.864806  1.277910  1.357581\n","54    10                      Ridge  0.572203  ...  0.893557  1.215844  1.504513\n","55    10              Random Forest  0.616028  ...  0.750408  1.191850  1.425367\n","56    10                      Lasso  0.590688  ...  0.864556  1.227404  1.471649\n","57    10               XGBRegressor  0.545758  ...  0.839365  1.339924  1.550317\n","58    10        Ensemble Avg Weight  0.613084  ...  0.760479  1.204986  1.430820\n","59    10  Ensemble Optimized Weight  0.627694  ...  0.743155  1.184959  1.403547\n","\n","[60 rows x 7 columns]"]},"metadata":{"tags":[]},"execution_count":15}]},{"cell_type":"code","metadata":{"id":"DT1IyMM4-4aj","executionInfo":{"status":"ok","timestamp":1625493899732,"user_tz":-330,"elapsed":4,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["df.to_csv(\"10runfulldata.csv\")"],"execution_count":36,"outputs":[]},{"cell_type":"code","metadata":{"id":"Sv2kj2WR03fV","executionInfo":{"status":"ok","timestamp":1625493714606,"user_tz":-330,"elapsed":642,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["df_complete = pd.DataFrame(columns=[\"RunNo\",\"Model\",\"R2score\",\"MSE\",\"MAE\",\"MAD\",\"RMSE\"])"],"execution_count":27,"outputs":[]},{"cell_type":"code","metadata":{"id":"ZTl3x1gM2Isx","executionInfo":{"status":"ok","timestamp":1625493498519,"user_tz":-330,"elapsed":2,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["model_name = [\"Ridge\",\"Random Forest\",\"Lasso\",\"XGBRegressor\",\"Ensemble Avg Weight\",\"Ensemble Optimized Weight\"]"],"execution_count":18,"outputs":[]},{"cell_type":"code","metadata":{"id":"sNYj67_09fzM","executionInfo":{"status":"ok","timestamp":1625493508207,"user_tz":-330,"elapsed":611,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["## Function to for final data\n","\n","for model in model_name:\n","  model_data = df[df.Model == model].mean()\n","  model_data['Model'] = model\n","  df_complete=df_complete.append(model_data,ignore_index=True)"],"execution_count":19,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":236},"id":"_gUy7Hwy-F-4","executionInfo":{"status":"ok","timestamp":1625493630485,"user_tz":-330,"elapsed":630,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"5427da8a-4c87-40f7-98fb-79f0f189dab4"},"source":["df_complete"],"execution_count":23,"outputs":[{"output_type":"execute_result","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>Model</th>\n","      <th>R2score</th>\n","      <th>MSE</th>\n","      <th>MAE</th>\n","      <th>MAD</th>\n","      <th>RMSE</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>Ridge</td>\n","      <td>0.467308</td>\n","      <td>2.262441</td>\n","      <td>0.995075</td>\n","      <td>1.166062</td>\n","      <td>1.502927</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>Random Forest</td>\n","      <td>0.503325</td>\n","      <td>2.102690</td>\n","      <td>0.904607</td>\n","      <td>1.119211</td>\n","      <td>1.448508</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>Lasso</td>\n","      <td>0.495505</td>\n","      <td>2.140811</td>\n","      <td>0.971763</td>\n","      <td>1.140973</td>\n","      <td>1.461473</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>XGBRegressor</td>\n","      <td>0.456983</td>\n","      <td>2.365155</td>\n","      <td>0.995805</td>\n","      <td>1.199010</td>\n","      <td>1.535331</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.516478</td>\n","      <td>2.061197</td>\n","      <td>0.910129</td>\n","      <td>1.121569</td>\n","      <td>1.434553</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.551953</td>\n","      <td>1.911102</td>\n","      <td>0.876255</td>\n","      <td>1.116479</td>\n","      <td>1.380748</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["                       Model   R2score       MSE       MAE       MAD      RMSE\n","0                      Ridge  0.467308  2.262441  0.995075  1.166062  1.502927\n","1              Random Forest  0.503325  2.102690  0.904607  1.119211  1.448508\n","2                      Lasso  0.495505  2.140811  0.971763  1.140973  1.461473\n","3               XGBRegressor  0.456983  2.365155  0.995805  1.199010  1.535331\n","4        Ensemble Avg Weight  0.516478  2.061197  0.910129  1.121569  1.434553\n","5  Ensemble Optimized Weight  0.551953  1.911102  0.876255  1.116479  1.380748"]},"metadata":{"tags":[]},"execution_count":23}]},{"cell_type":"code","metadata":{"id":"I7_040-_9pbe","executionInfo":{"status":"ok","timestamp":1625493592131,"user_tz":-330,"elapsed":622,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["df_complete =df_complete.drop(columns=\"RunNo\")"],"execution_count":22,"outputs":[]},{"cell_type":"code","metadata":{"id":"j9Z3rKu7-B1Z","executionInfo":{"status":"ok","timestamp":1625493650849,"user_tz":-330,"elapsed":611,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["df_complete.to_csv(\"10runMeandata.csv\")"],"execution_count":24,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"aDUZcppt-TJW"},"source":["For std\n"]},{"cell_type":"code","metadata":{"id":"y-xpU6C0-NzC","executionInfo":{"status":"ok","timestamp":1625493717635,"user_tz":-330,"elapsed":689,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["for model in model_name:\n","  model_data = df[df.Model == model].std()\n","  model_data['Model'] = model\n","  df_complete=df_complete.append(model_data,ignore_index=True)"],"execution_count":28,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":236},"id":"VMTs_u_m-W9m","executionInfo":{"status":"ok","timestamp":1625493719508,"user_tz":-330,"elapsed":5,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"1a0eb643-989e-4dbb-8f9a-44220659fd26"},"source":["df_complete =df_complete.drop(columns=\"RunNo\")\n","df_complete"],"execution_count":29,"outputs":[{"output_type":"execute_result","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>Model</th>\n","      <th>R2score</th>\n","      <th>MSE</th>\n","      <th>MAE</th>\n","      <th>MAD</th>\n","      <th>RMSE</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>Ridge</td>\n","      <td>0.224334</td>\n","      <td>0.193040</td>\n","      <td>0.085861</td>\n","      <td>0.198216</td>\n","      <td>0.063697</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>Random Forest</td>\n","      <td>0.211714</td>\n","      <td>0.205417</td>\n","      <td>0.090831</td>\n","      <td>0.237669</td>\n","      <td>0.070819</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>Lasso</td>\n","      <td>0.212926</td>\n","      <td>0.215596</td>\n","      <td>0.085306</td>\n","      <td>0.195177</td>\n","      <td>0.073841</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>XGBRegressor</td>\n","      <td>0.180672</td>\n","      <td>0.287416</td>\n","      <td>0.124097</td>\n","      <td>0.217933</td>\n","      <td>0.093780</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.196234</td>\n","      <td>0.171672</td>\n","      <td>0.096765</td>\n","      <td>0.214654</td>\n","      <td>0.060129</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.177909</td>\n","      <td>0.197642</td>\n","      <td>0.091323</td>\n","      <td>0.202163</td>\n","      <td>0.071773</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["                       Model   R2score       MSE       MAE       MAD      RMSE\n","0                      Ridge  0.224334  0.193040  0.085861  0.198216  0.063697\n","1              Random Forest  0.211714  0.205417  0.090831  0.237669  0.070819\n","2                      Lasso  0.212926  0.215596  0.085306  0.195177  0.073841\n","3               XGBRegressor  0.180672  0.287416  0.124097  0.217933  0.093780\n","4        Ensemble Avg Weight  0.196234  0.171672  0.096765  0.214654  0.060129\n","5  Ensemble Optimized Weight  0.177909  0.197642  0.091323  0.202163  0.071773"]},"metadata":{"tags":[]},"execution_count":29}]},{"cell_type":"code","metadata":{"id":"TJ8W7b4e-l49","executionInfo":{"status":"ok","timestamp":1625493778507,"user_tz":-330,"elapsed":629,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}}},"source":["df_complete.to_csv(\"10runSTDdata.csv\")"],"execution_count":31,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":362},"id":"ZV86A8IDTr57","executionInfo":{"status":"ok","timestamp":1625484305557,"user_tz":-330,"elapsed":37,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"3b950b00-b449-446c-df1f-f462a576ac2d"},"source":["df_weights"],"execution_count":null,"outputs":[{"output_type":"execute_result","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>RunNo</th>\n","      <th>Ridge</th>\n","      <th>Random Forest</th>\n","      <th>Lasso</th>\n","      <th>XGBREGRESSOR</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>1.0</td>\n","      <td>-0.027488</td>\n","      <td>0.317904</td>\n","      <td>0.726325</td>\n","      <td>-0.045743</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>2.0</td>\n","      <td>-0.528298</td>\n","      <td>0.492890</td>\n","      <td>0.501537</td>\n","      <td>0.500974</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>3.0</td>\n","      <td>-0.316934</td>\n","      <td>0.382628</td>\n","      <td>0.594565</td>\n","      <td>0.325940</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>4.0</td>\n","      <td>-0.157894</td>\n","      <td>0.012585</td>\n","      <td>0.994035</td>\n","      <td>0.144809</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>5.0</td>\n","      <td>-0.018221</td>\n","      <td>1.252257</td>\n","      <td>0.093711</td>\n","      <td>-0.255934</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>6.0</td>\n","      <td>0.044168</td>\n","      <td>0.113342</td>\n","      <td>0.906734</td>\n","      <td>-0.053208</td>\n","    </tr>\n","    <tr>\n","      <th>6</th>\n","      <td>7.0</td>\n","      <td>-0.086389</td>\n","      <td>0.216811</td>\n","      <td>0.786512</td>\n","      <td>0.082313</td>\n","    </tr>\n","    <tr>\n","      <th>7</th>\n","      <td>8.0</td>\n","      <td>-0.229062</td>\n","      <td>0.187379</td>\n","      <td>0.896688</td>\n","      <td>0.184318</td>\n","    </tr>\n","    <tr>\n","      <th>8</th>\n","      <td>9.0</td>\n","      <td>-0.125054</td>\n","      <td>0.557077</td>\n","      <td>0.654084</td>\n","      <td>-0.160627</td>\n","    </tr>\n","    <tr>\n","      <th>9</th>\n","      <td>10.0</td>\n","      <td>-0.182442</td>\n","      <td>0.425205</td>\n","      <td>0.551643</td>\n","      <td>0.173562</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["   RunNo     Ridge  Random Forest     Lasso  XGBREGRESSOR\n","0    1.0 -0.027488       0.317904  0.726325     -0.045743\n","1    2.0 -0.528298       0.492890  0.501537      0.500974\n","2    3.0 -0.316934       0.382628  0.594565      0.325940\n","3    4.0 -0.157894       0.012585  0.994035      0.144809\n","4    5.0 -0.018221       1.252257  0.093711     -0.255934\n","5    6.0  0.044168       0.113342  0.906734     -0.053208\n","6    7.0 -0.086389       0.216811  0.786512      0.082313\n","7    8.0 -0.229062       0.187379  0.896688      0.184318\n","8    9.0 -0.125054       0.557077  0.654084     -0.160627\n","9   10.0 -0.182442       0.425205  0.551643      0.173562"]},"metadata":{"tags":[]},"execution_count":15}]},{"cell_type":"code","metadata":{"id":"I2g8DYJI-LPk"},"source":[""],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"uJ3c7HxtX11_","executionInfo":{"status":"ok","timestamp":1625484305558,"user_tz":-330,"elapsed":34,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"5fb1c430-283e-419e-f5bb-09eb1e22e9d9"},"source":["df_weights.mean()"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["RunNo            5.500000\n","Ridge           -0.162762\n","Random Forest    0.395808\n","Lasso            0.670583\n","XGBREGRESSOR     0.089640\n","dtype: float64"]},"metadata":{"tags":[]},"execution_count":16}]},{"cell_type":"code","metadata":{"id":"C407QIQ6YA9Q"},"source":["df_weights_std = df_weights.std()"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"IEc-kqANYR1I","executionInfo":{"status":"ok","timestamp":1625484305558,"user_tz":-330,"elapsed":24,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"996ca07d-bdd9-44b4-95ac-c91269b485d2"},"source":["df_weights_std"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["RunNo            3.027650\n","Ridge            0.167152\n","Random Forest    0.346117\n","Lasso            0.260259\n","XGBREGRESSOR     0.227285\n","dtype: float64"]},"metadata":{"tags":[]},"execution_count":18}]},{"cell_type":"code","metadata":{"id":"VPz3NSUMYA_J"},"source":["df_weights_std.to_csv(\"10RunWeigthsSTD.csv\")"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"ccyQiURS4Kcw"},"source":["## Function to for final data\n","\n","for model in model_name:\n","  model_data = df[df.Model == model].mean()\n","  model_data['Model'] = model\n","  df_complete=df_complete.append(model_data,ignore_index=True)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"4lsBGhB-49Vc","colab":{"base_uri":"https://localhost:8080/","height":236},"executionInfo":{"status":"ok","timestamp":1625484305560,"user_tz":-330,"elapsed":22,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"658737a4-82e3-4166-b190-78c65a881e8c"},"source":["df_complete.drop(columns=\"RunNo\")"],"execution_count":null,"outputs":[{"output_type":"execute_result","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>Model</th>\n","      <th>R2score</th>\n","      <th>MSE</th>\n","      <th>MAE</th>\n","      <th>MAD</th>\n","      <th>RMSE</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>Ridge</td>\n","      <td>0.455998</td>\n","      <td>2.085165</td>\n","      <td>0.979337</td>\n","      <td>1.056041</td>\n","      <td>1.417506</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>Random Forest</td>\n","      <td>0.486225</td>\n","      <td>2.005830</td>\n","      <td>0.893762</td>\n","      <td>0.912662</td>\n","      <td>1.399422</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>Lasso</td>\n","      <td>0.524725</td>\n","      <td>1.865426</td>\n","      <td>0.908892</td>\n","      <td>0.983907</td>\n","      <td>1.348018</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>XGBRegressor</td>\n","      <td>0.437293</td>\n","      <td>2.216104</td>\n","      <td>0.980795</td>\n","      <td>1.062178</td>\n","      <td>1.470480</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.528191</td>\n","      <td>1.859070</td>\n","      <td>0.872359</td>\n","      <td>0.946105</td>\n","      <td>1.343952</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.561623</td>\n","      <td>1.721566</td>\n","      <td>0.855829</td>\n","      <td>0.949139</td>\n","      <td>1.294207</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["                       Model   R2score       MSE       MAE       MAD      RMSE\n","0                      Ridge  0.455998  2.085165  0.979337  1.056041  1.417506\n","1              Random Forest  0.486225  2.005830  0.893762  0.912662  1.399422\n","2                      Lasso  0.524725  1.865426  0.908892  0.983907  1.348018\n","3               XGBRegressor  0.437293  2.216104  0.980795  1.062178  1.470480\n","4        Ensemble Avg Weight  0.528191  1.859070  0.872359  0.946105  1.343952\n","5  Ensemble Optimized Weight  0.561623  1.721566  0.855829  0.949139  1.294207"]},"metadata":{"tags":[]},"execution_count":23}]},{"cell_type":"code","metadata":{"id":"cY7uivt55ImP"},"source":["df_complete.to_csv(\"10runMeanData.csv\")"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"tGOW-Pxe5rQ0"},"source":["for model in model_name:\n","  model_data = df[df.Model == model].std()\n","  model_data['Model'] = model\n","  df_complete=df_complete.append(model_data,ignore_index=True)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"xT9bddgM568z","colab":{"base_uri":"https://localhost:8080/","height":425},"executionInfo":{"status":"ok","timestamp":1625484305564,"user_tz":-330,"elapsed":24,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"e54d48ab-2eeb-4761-9ad2-59bff31ede82"},"source":["df_complete.drop(columns=\"RunNo\")"],"execution_count":null,"outputs":[{"output_type":"execute_result","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>Model</th>\n","      <th>R2score</th>\n","      <th>MSE</th>\n","      <th>MAE</th>\n","      <th>MAD</th>\n","      <th>RMSE</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>Ridge</td>\n","      <td>0.455998</td>\n","      <td>2.085165</td>\n","      <td>0.979337</td>\n","      <td>1.056041</td>\n","      <td>1.417506</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>Random Forest</td>\n","      <td>0.486225</td>\n","      <td>2.005830</td>\n","      <td>0.893762</td>\n","      <td>0.912662</td>\n","      <td>1.399422</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>Lasso</td>\n","      <td>0.524725</td>\n","      <td>1.865426</td>\n","      <td>0.908892</td>\n","      <td>0.983907</td>\n","      <td>1.348018</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>XGBRegressor</td>\n","      <td>0.437293</td>\n","      <td>2.216104</td>\n","      <td>0.980795</td>\n","      <td>1.062178</td>\n","      <td>1.470480</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.528191</td>\n","      <td>1.859070</td>\n","      <td>0.872359</td>\n","      <td>0.946105</td>\n","      <td>1.343952</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.561623</td>\n","      <td>1.721566</td>\n","      <td>0.855829</td>\n","      <td>0.949139</td>\n","      <td>1.294207</td>\n","    </tr>\n","    <tr>\n","      <th>6</th>\n","      <td>Ridge</td>\n","      <td>0.264023</td>\n","      <td>0.857298</td>\n","      <td>0.185665</td>\n","      <td>0.215391</td>\n","      <td>0.290290</td>\n","    </tr>\n","    <tr>\n","      <th>7</th>\n","      <td>Random Forest</td>\n","      <td>0.137990</td>\n","      <td>0.662433</td>\n","      <td>0.089346</td>\n","      <td>0.249026</td>\n","      <td>0.229609</td>\n","    </tr>\n","    <tr>\n","      <th>8</th>\n","      <td>Lasso</td>\n","      <td>0.130176</td>\n","      <td>0.651156</td>\n","      <td>0.094386</td>\n","      <td>0.183399</td>\n","      <td>0.231596</td>\n","    </tr>\n","    <tr>\n","      <th>9</th>\n","      <td>XGBRegressor</td>\n","      <td>0.147668</td>\n","      <td>0.737115</td>\n","      <td>0.099116</td>\n","      <td>0.187342</td>\n","      <td>0.244474</td>\n","    </tr>\n","    <tr>\n","      <th>10</th>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.132693</td>\n","      <td>0.677872</td>\n","      <td>0.089788</td>\n","      <td>0.197468</td>\n","      <td>0.242357</td>\n","    </tr>\n","    <tr>\n","      <th>11</th>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.124520</td>\n","      <td>0.611741</td>\n","      <td>0.126013</td>\n","      <td>0.182561</td>\n","      <td>0.227533</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["                        Model   R2score       MSE       MAE       MAD      RMSE\n","0                       Ridge  0.455998  2.085165  0.979337  1.056041  1.417506\n","1               Random Forest  0.486225  2.005830  0.893762  0.912662  1.399422\n","2                       Lasso  0.524725  1.865426  0.908892  0.983907  1.348018\n","3                XGBRegressor  0.437293  2.216104  0.980795  1.062178  1.470480\n","4         Ensemble Avg Weight  0.528191  1.859070  0.872359  0.946105  1.343952\n","5   Ensemble Optimized Weight  0.561623  1.721566  0.855829  0.949139  1.294207\n","6                       Ridge  0.264023  0.857298  0.185665  0.215391  0.290290\n","7               Random Forest  0.137990  0.662433  0.089346  0.249026  0.229609\n","8                       Lasso  0.130176  0.651156  0.094386  0.183399  0.231596\n","9                XGBRegressor  0.147668  0.737115  0.099116  0.187342  0.244474\n","10        Ensemble Avg Weight  0.132693  0.677872  0.089788  0.197468  0.242357\n","11  Ensemble Optimized Weight  0.124520  0.611741  0.126013  0.182561  0.227533"]},"metadata":{"tags":[]},"execution_count":26}]},{"cell_type":"code","metadata":{"id":"I38BCso26AAF"},"source":["df_complete.to_csv(\"10runSTDdata.csv\")"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"oKAwZJN7IZja"},"source":["## Plots to be done:\n","1. Model comparison\n","2.\n"]},{"cell_type":"code","metadata":{"id":"8TXOkcyUZmYh"},"source":["df_mean=  pd.read_csv(\"/gdrive/MyDrive/10runMeanData.csv\")"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":271},"id":"8rkJhURRaUvV","executionInfo":{"status":"ok","timestamp":1625484306284,"user_tz":-330,"elapsed":14,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"9ab6d831-1029-428e-973f-4a284982ca61"},"source":["df_mean"],"execution_count":null,"outputs":[{"output_type":"execute_result","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>Unnamed: 0</th>\n","      <th>RunNo</th>\n","      <th>Model</th>\n","      <th>R2score</th>\n","      <th>MSE</th>\n","      <th>MAE</th>\n","      <th>MAD</th>\n","      <th>RMSE</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>0</td>\n","      <td>5.5</td>\n","      <td>Ridge</td>\n","      <td>0.792225</td>\n","      <td>1.121012</td>\n","      <td>0.777161</td>\n","      <td>1.280957</td>\n","      <td>1.058779</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>1</td>\n","      <td>5.5</td>\n","      <td>Random Forest</td>\n","      <td>0.676428</td>\n","      <td>1.745773</td>\n","      <td>0.843900</td>\n","      <td>1.229489</td>\n","      <td>1.320696</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2</td>\n","      <td>5.5</td>\n","      <td>Lasso</td>\n","      <td>0.800742</td>\n","      <td>1.075062</td>\n","      <td>0.762306</td>\n","      <td>1.300393</td>\n","      <td>1.036852</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>3</td>\n","      <td>5.5</td>\n","      <td>XGBRegressor</td>\n","      <td>0.708955</td>\n","      <td>1.570279</td>\n","      <td>0.808592</td>\n","      <td>1.309301</td>\n","      <td>1.253108</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>4</td>\n","      <td>5.5</td>\n","      <td>Ensemble Avg Weight</td>\n","      <td>0.777111</td>\n","      <td>1.202557</td>\n","      <td>0.722876</td>\n","      <td>1.250584</td>\n","      <td>1.096570</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>5</td>\n","      <td>5.5</td>\n","      <td>Ensemble Optimized Weight</td>\n","      <td>0.808416</td>\n","      <td>1.033654</td>\n","      <td>0.772433</td>\n","      <td>1.264139</td>\n","      <td>1.016686</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["   Unnamed: 0  RunNo                      Model  ...       MAE       MAD      RMSE\n","0           0    5.5                      Ridge  ...  0.777161  1.280957  1.058779\n","1           1    5.5              Random Forest  ...  0.843900  1.229489  1.320696\n","2           2    5.5                      Lasso  ...  0.762306  1.300393  1.036852\n","3           3    5.5               XGBRegressor  ...  0.808592  1.309301  1.253108\n","4           4    5.5        Ensemble Avg Weight  ...  0.722876  1.250584  1.096570\n","5           5    5.5  Ensemble Optimized Weight  ...  0.772433  1.264139  1.016686\n","\n","[6 rows x 8 columns]"]},"metadata":{"tags":[]},"execution_count":29}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"oxjJ2UPQaiZD","executionInfo":{"status":"ok","timestamp":1625484306285,"user_tz":-330,"elapsed":14,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"4a9ba338-96bd-4e88-946b-95f838840a7d"},"source":["df_mean.R2score[0]"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["0.7922249168951029"]},"metadata":{"tags":[]},"execution_count":30}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":441},"id":"0xONMqOpaVpt","executionInfo":{"status":"ok","timestamp":1625484306285,"user_tz":-330,"elapsed":11,"user":{"displayName":"Atharv Jairath","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GimYmfxjyVhkyags-cPXU89M7YrR7p8lIrOncB55kc=s64","userId":"02765993908853204784"}},"outputId":"f1eae313-bf88-42da-9e94-ccf2b695a4b7"},"source":["fig = plt.figure(figsize=(7,5))\n","ax = fig.add_axes([0,0,1,1])\n","models = ['Ridge',  'Random Forest', 'LASSO','XGBRegressor', 'Ensemble']\n","\n","r2_score_list = [round(df_mean.R2score[0],3),\n","                 round(df_mean.R2score[1],3),\n","                 round(df_mean.R2score[2],3),\n","                 round(df_mean.R2score[3],3),\n","                 round(df_mean.R2score[5],3)\n","                 ]\n","\n","ax.bar(models,r2_score_list)\n","ax.set_ylabel('R2 Score',fontsize= 12)\n","ax.set_xlabel('Models',fontsize= 12)\n","ax.set_title('Model Comparison')\n","for i, v in enumerate(r2_score_list):\n","  ax.text(i - 0.1,v + 0.01, str(v), color='black', fontweight='bold')\n","#plt.savefig('barplot_1.png',dpi=200, format='png', bbox_inches='tight')\n","plt.show()"],"execution_count":null,"outputs":[{"output_type":"display_data","data":{"image/png":"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\n","text/plain":["<Figure size 504x360 with 1 Axes>"]},"metadata":{"tags":[],"needs_background":"light"}}]}]}