{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: pandas in c:\\programdata\\anaconda3\\lib\\site-packages (0.24.2)\n",
"Requirement already satisfied: pytz>=2011k in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (2018.9)\n",
"Requirement already satisfied: python-dateutil>=2.5.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (2.8.0)\n",
"Requirement already satisfied: numpy>=1.12.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (1.16.2)\n",
"Requirement already satisfied: six>=1.5 in c:\\programdata\\anaconda3\\lib\\site-packages (from python-dateutil>=2.5.0->pandas) (1.12.0)\n",
"Requirement already satisfied: xlrd in c:\\programdata\\anaconda3\\lib\\site-packages (1.2.0)\n",
"Requirement already satisfied: sklearn in c:\\programdata\\anaconda3\\lib\\site-packages (0.0)\n",
"Requirement already satisfied: scikit-learn in c:\\programdata\\anaconda3\\lib\\site-packages (from sklearn) (0.21.2)\n",
"Requirement already satisfied: scipy>=0.17.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from scikit-learn->sklearn) (1.2.1)\n",
"Requirement already satisfied: joblib>=0.11 in c:\\programdata\\anaconda3\\lib\\site-packages (from scikit-learn->sklearn) (0.13.2)\n",
"Requirement already satisfied: numpy>=1.11.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from scikit-learn->sklearn) (1.16.2)\n",
"Requirement already satisfied: imblearn in c:\\programdata\\anaconda3\\lib\\site-packages (0.0)\n",
"Requirement already satisfied: imbalanced-learn in c:\\programdata\\anaconda3\\lib\\site-packages (from imblearn) (0.5.0)\n",
"Requirement already satisfied: joblib>=0.11 in c:\\programdata\\anaconda3\\lib\\site-packages (from imbalanced-learn->imblearn) (0.13.2)\n",
"Requirement already satisfied: scipy>=0.17 in c:\\programdata\\anaconda3\\lib\\site-packages (from imbalanced-learn->imblearn) (1.2.1)\n",
"Requirement already satisfied: numpy>=1.11 in c:\\programdata\\anaconda3\\lib\\site-packages (from imbalanced-learn->imblearn) (1.16.2)\n",
"Requirement already satisfied: scikit-learn>=0.21 in c:\\programdata\\anaconda3\\lib\\site-packages (from imbalanced-learn->imblearn) (0.21.2)\n"
]
}
],
"source": [
"!pip install pandas\n",
"!pip install xlrd\n",
"!pip install sklearn\n",
"!pip install imblearn"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import xlrd\n",
"book = xlrd.open_workbook(\"Datasheets info.xlsx\")\n",
"sheetMQ2 = book.sheet_by_name(\"MQ2 - Pololulu\")\n",
"sheetMQ3 = book.sheet_by_name(\"MQ3 - Sparkfun\")\n",
"sheetMQ4 = book.sheet_by_name(\"MQ4 - Sparkfun\")\n",
"sheetMQ5 = book.sheet_by_name(\"MQ5 - Sparkfun\")\n",
"sheetMQ6 = book.sheet_by_name(\"MQ6 - Sparkfun\")\n",
"sheetMQ7 = book.sheet_by_name(\"MQ7 - Sparkfun\")\n",
"sheetMQ8 = book.sheet_by_name(\"MQ8 - Sparkfun\")\n",
"sheetMQ9 = book.sheet_by_name(\"MQ9 - Haoyuelectronics\")\n",
"sheetMQ131 = book.sheet_by_name(\"MQ131- Sensorsportal\")\n",
"sheetMQ135 = book.sheet_by_name(\"MQ135 - HANWEI\")\n",
"sheetMQ303A = book.sheet_by_name(\"MQ303A - HANWEI\")\n",
"sheetMQ309A = book.sheet_by_name(\"MQ309A - HANWEI\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.1 \t \t \t \t \n",
"0.2 \t \t 5000.0 \t \t \n",
"0.3 \t \t \t \t \n",
"0.4 \t \t 800.0 \t 2000.0 \t \n",
"0.5 \t \t \t 1000.0 \t \n",
"0.6 \t \t \t \t \n",
"0.7 \t 5000.0 \t 200.0 \t 500.0 \t \n",
"0.8 \t 2000.0 \t \t \t \n",
"0.9 \t \t \t \t \n",
"1.0 \t 1000.0 \t \t \t \n",
"2.0 \t \t \t \t \n",
"3.0 \t \t \t \t 800.0\n",
"4.0 \t \t \t \t 200.0\n",
"5.0 \t \t \t \t \n",
"6.0 \t \t \t \t \n",
"7.0 \t \t \t \t \n",
"8.0 \t \t \t \t \n",
"9.0 \t \t \t \t \n",
"10.0 \t \t \t \t \n"
]
}
],
"source": [
"for row_index in range(1,20): #reading first columns\n",
" RsR0, H2, LPG , CH4, CO = sheetMQ5.row_values(row_index, start_colx=0, end_colx=5)\n",
" print(RsR0, \"\t\", H2, \"\t\", LPG, \"\t\", CH4, \"\t\", CO)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"x_MQ5 = sheetMQ5.col_values(0)[2:]\n",
"MQ5_H2 = sheetMQ5.col_values(1)[2:]\n",
"MQ5_LPG = sheetMQ5.col_values(2)[2:]\n",
"MQ5_CH4 = sheetMQ5.col_values(3)[2:]\n",
"MQ5_CO = sheetMQ5.col_values(4)[2:]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"def zero_to_nan(values):\n",
" \"\"\"Replace every 0 with 'nan' and return a copy.\"\"\"\n",
" return [float('nan') if x==0 else x for x in values]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"MQ5_H2 =zero_to_nan(MQ5_H2)\n",
"MQ5_LPG =zero_to_nan(MQ5_LPG)\n",
"MQ5_CH4 =zero_to_nan(MQ5_CH4)\n",
"MQ5_CO =zero_to_nan(MQ5_CO)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"scrolled": false
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.datasets import load_iris\n",
"#from sklearn.cross_validation import train_test_split\n",
"from sklearn.tree import DecisionTreeClassifier\n",
"from sklearn import datasets\n",
"from sklearn import linear_model\n",
"\n",
"dataH2 = {'RsRo': x_MQ5, 'H2': MQ5_H2}\n",
"dataLPG = {'RsRo': x_MQ5, 'LPG': MQ5_LPG}\n",
"dataCH4 = {'RsRo': x_MQ5, 'CH4': MQ5_CH4}\n",
"dataCO = {'RsRo': x_MQ5, 'CO': MQ5_CO}\n",
"\n",
"dfMQ5_H2 = pd.DataFrame(dataH2)\n",
"dfMQ5_LPG = pd.DataFrame(dataLPG)\n",
"dfMQ5_CH4 = pd.DataFrame(dataCH4)\n",
"dfMQ5_CO = pd.DataFrame(dataCO)\n",
"\n",
"dfMQ5_H2['H2'] = pd.to_numeric(dfMQ5_H2['H2'])\n",
"dfMQ5_LPG['LPG'] = pd.to_numeric(dfMQ5_LPG['LPG'])\n",
"dfMQ5_CH4['CH4'] = pd.to_numeric(dfMQ5_CH4['CH4'])\n",
"dfMQ5_CO['CO'] = pd.to_numeric(dfMQ5_CO['CO'])\n",
"\n",
"dfMQ5_H2['H2'] = dfMQ5_H2['H2'].replace('',None, regex=True)\n",
"dfMQ5_LPG['LPG'] = dfMQ5_LPG['LPG'].replace('',None, regex=True)\n",
"dfMQ5_CH4['CH4'] = dfMQ5_CH4['CH4'].replace('',None, regex=True)\n",
"dfMQ5_CO['CO'] = dfMQ5_CO['CO'].replace('',None, regex=True)\n",
"\n",
"#Global X_Predict variable\n",
"X_Predict = dfMQ5_LPG.RsRo.apply(lambda x: [x]).tolist()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"#Model and train H2\n",
"dataset2TrainH2 = dfMQ5_H2.copy()\n",
"dataset2TrainH2.dropna(inplace=True)\n",
"X_trainH2 = dataset2TrainH2.RsRo.apply(lambda x: [x]).tolist()\n",
"y_trainH2 = dataset2TrainH2['H2'].tolist()\n",
"model = linear_model.Lasso(alpha=0.1)\n",
"model.fit(X_trainH2, y_trainH2)\n",
"#Predict\n",
"H2_Predicted = model.predict(X_Predict)\n",
"#save into MQ2\n",
"MQ5_H2 = H2_Predicted\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"#Model and train LPG\n",
"dataset2TrainLPG = dfMQ5_LPG.copy()\n",
"dataset2TrainLPG.dropna(inplace=True)\n",
"X_trainLPG = dataset2TrainLPG.RsRo.apply(lambda x: [x]).tolist()\n",
"y_trainLPG = dataset2TrainLPG['LPG'].tolist()\n",
"model = linear_model.Lasso(alpha=0.1)\n",
"model.fit(X_trainLPG, y_trainLPG)\n",
"#Predict\n",
"LPG_Predicted = model.predict(X_Predict)\n",
"#save into MQ2\n",
"MQ5_LPG = LPG_Predicted"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"#Model and train CH4\n",
"dataset2TrainCH4 = dfMQ5_CH4.copy()\n",
"dataset2TrainCH4.dropna(inplace=True)\n",
"X_trainCH4 = dataset2TrainCH4.RsRo.apply(lambda x: [x]).tolist()\n",
"y_trainCH4 = dataset2TrainCH4['CH4'].tolist()\n",
"model = linear_model.Lasso(alpha=0.1)\n",
"model.fit(X_trainCH4, y_trainCH4)\n",
"#Predict\n",
"CH4_Predicted = model.predict(X_Predict)\n",
"#save into MQ2\n",
"MQ5_CH4 = CH4_Predicted"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"#Model and train CO\n",
"dataset2TrainCO = dfMQ5_CO.copy()\n",
"dataset2TrainCO.dropna(inplace=True)\n",
"X_trainCO = dataset2TrainCO.RsRo.apply(lambda x: [x]).tolist()\n",
"y_trainCO = dataset2TrainCO['CO'].tolist()\n",
"model = linear_model.Lasso(alpha=0.1)\n",
"model.fit(X_trainCO, y_trainCO)\n",
"#Predict\n",
"CO_Predicted = model.predict(X_Predict)\n",
"#save into MQ2\n",
"MQ5_CO = CO_Predicted"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"image/svg+xml": [
"\r\n",
"\r\n",
"\r\n",
"\r\n"
],
"text/plain": [
""
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"%config InlineBackend.figure_formats = ['svg']\n",
"%matplotlib inline\n",
"import matplotlib.pyplot as plt\n",
"import matplotlib.lines as mlines\n",
"import matplotlib.transforms as mtransforms\n",
"\n",
"fig, ax = plt.subplots()\n",
"\n",
"fig.set_size_inches(9, 5.5, forward=True)\n",
"fig.set_dpi(200)\n",
"\n",
"# only these two lines are calibration curves\n",
"plt.plot(MQ5_H2, x_MQ5, marker='o', linewidth=1, label='H2')\n",
"plt.plot(MQ5_LPG, x_MQ5, marker='o', linewidth=1, label='LPG')\n",
"plt.plot(MQ5_CH4, x_MQ5, marker='o', linewidth=1, label='CH4')\n",
"plt.plot(MQ5_CO, x_MQ5, marker='o', linewidth=1, label='CO')\n",
"\n",
"\n",
"# reference line, legends, and axis labels\n",
"#line = mlines.Line2D([0, 1], [0, 1], color='black')\n",
"#transform = ax.transAxes\n",
"#line.set_transform(transform)\n",
"#ax.add_line(line)\n",
"plt.yscale('log')\n",
"plt.xscale('log')\n",
"plt.legend()\n",
"\n",
"plt.grid(b=True, which='minor', color='lightgrey', linestyle='--')\n",
"\n",
"fig.suptitle('Calibration plot for MQ-5 data')\n",
"ax.set_xlabel('PPM Concentration')\n",
"ax.set_ylabel('Rs/Ro')\n",
"\n",
"\n",
"#Save image\n",
"plt.savefig('MQ5.svg', format = 'svg', dpi = 1200)\n",
"plt.savefig('MQ5.png')\n",
"plt.savefig('MQ5.eps', format = 'eps', dpi = 1200)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}