{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "from glob import glob"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def read_data(filename):\n",
    "    data=np.genfromtxt(filename, delimiter=\",\",skip_header=1, dtype=float).T\n",
    "    wavelengths=data[0]\n",
    "    intensity=data[1::2] #takes each other column , where column # is matched with the run #\n",
    "    return wavelengths,intensity\n",
    "    \"\"\"\n",
    "    Function that reads data:\n",
    "    imput is the file that will be taken from specified directory\n",
    "    \n",
    "    genfromtxt is a function that reads csv files, where the imputs of the read_data are \n",
    "    filename - the file that it will be reading from\n",
    "    delimiter- is a character that separates values in the file\n",
    "    skip_header-skips the header of the file where it is just the titles and not part of the data\n",
    "    dtype-the type that the data will be in, in this case it will be float, non integer number \n",
    "    All of this is stored in data.\n",
    "    \n",
    "    wavelengths will have the first column in the data\n",
    "    intensity will begin with the second and skip every other column\n",
    "    \n",
    "    thus your imput is the file with the data you would like to analyse and its outputs are\n",
    "    wavelengths and the intensity\n",
    "    \n",
    "    \"\"\"\n",
    "    \n",
    "def plot_raw_data(wavelengths, intensity, dr, save, plotname): #feed those from the above read_data function into this one\n",
    "    Nruns=intensity.shape[0]\n",
    "    r=(np.arange(Nruns)-Nruns/2.)/(0.5*Nruns) + dr\n",
    "    bolIntensity=intensity.sum(axis=1) #adding up the intensity of rows, not the columns, sums up for all of the intensity in all wavelengths for 1 run, intensity as the function of the run. \n",
    "    \"\"\"plot_raw_data is a function that takes the wavelenghts and the intensity from the output of read_data\n",
    "    function, dr that will be found manually, creates a plot saves it and then names it\n",
    "\n",
    "    Nruns is technically a tuple that has the shape of the intensity in the form of (#columns, #rows) here is just a number\n",
    "    and its the size of the dimension of intensity. \n",
    "    r is the range of Nruns from the xminimum to xmaximum, in this case \n",
    "    taking data points and making an assumption that they are evenly spaced and mapping them across the disk of \n",
    "    the sun, no blank spaces. Also assuming that we started on the edge of the sun (which on its own can be a limitation). \n",
    "    +dr is a corrective measure to shift to where the centre is. \n",
    "    bolIntensity is the bolimetric Intensity where the intensity is added up in rowns, not in columns. \"\"\"\n",
    "\n",
    "    plt.plot(r[r>0], bolIntensity[r>0],color=\"r\") \n",
    "    \"\"\"grabbing the right side of the sun where r is greater than 0, bolIntensity is also greater than \n",
    "    0, color coded as red\"\"\"\n",
    "    plt.plot(-r[r<=0], bolIntensity[r<=0], color=\"b\") \n",
    "    \"\"\"grabbing the left of the sun where the radius is greater or equal to 0 and flipping it over. OVERLAP!!\"\"\"\n",
    "    plt.xlabel(\"radius/RSun\") #labels the x axis radius/RSun \n",
    "    plt.ylabel(\"intensity\") #labels the y axis as intensity\n",
    "     #\"\"\"if then loop where if save is true, then save plot as (name the plot here), else show the plot \"\"\"\n",
    "    if save:\n",
    "        plt.savefig(plotname) \n",
    "    else:        \n",
    "        plt.show()\n",
    "\n",
    "\n",
    "\n",
    "def mu_plot(wavelength, intensity, dr, stretch, plotname, Lambda, colors): #I(mu)\n",
    "    \"\"\"function that plots mu where the imputs are wavelength and intensity acquired from reading the data\n",
    "    dr-corrective measure that will shift data to where the center of the sun is. (acquired in the next cell) \n",
    "    stretch that allows r to be greater than 1\n",
    "    plotname where you name the plot when it saves \n",
    "    Lambda are the wavelengths that you want to analyse\n",
    "    colors are the colors that you want Lambda represented as\n",
    "    \n",
    "    Nruns is a tuple that has the shape of the intensity in the form of (#columns, #rows), in this case its just a number\n",
    "    and its the size of the dimension of intensity\"\"\"\n",
    "    Nruns=intensity.shape[0]\n",
    "    r=((np.arange(Nruns)-Nruns/2.)/(0.5*Nruns) + dr)*stretch # stretch lets little r be greater than 1\n",
    "    \n",
    "    \n",
    "    \"\"\"if we have blank spaces in the spectrum, and has noise, that are off the radius of the sun\n",
    "    allows to account for whats off the radius of the sun .\n",
    "    grab all of the positive and negative values of r and take their absolute value and sort them in order. \n",
    "    mu is the equation that we need for mu, whatever, you know what I mean. \n",
    "    \n",
    "    second mu stacks horizontally the values obtained from the mu equation where r is greater than 0, and mu \n",
    "    less than or equal to 0. \n",
    "    taking all the mu values for a run and collapsing it into one\n",
    "    \"\"\"\n",
    "    #\"\"\"List lambda that has all wavelengths that we want, we are finding for a specific wavelength its position in the wavelength array where the data was taken.\"\"\"\n",
    "    \n",
    "    mu = np.sqrt(1-r**2)\n",
    "    mu = np.hstack((mu[r>0],mu[r<=0])) # calculate mu in the same order that we are going to calculate I(mu)\n",
    "    \n",
    "    for i in range(len(Lambda)):  #plot several different wavelenghts in different colours \n",
    "        w=np.argmin(np.abs(wavelength-Lambda[i]))\n",
    "        i_mu=np.hstack((intensity[r>0, w], intensity[r<=0, w])) #taking right and left hands sides putting them together and sorting them by location on the sun \n",
    "        #same order as the mu intensity of the mu that we have found. \n",
    "        \"\"\"intensity at that wavelength and stack them in left and right\"\"\"\n",
    "        i_mu/=i_mu.max() #normalisation. \n",
    "        plt.plot(mu, i_mu, color=colors[i], label=Lambda[i])#r values in the same order as the intensity, -1's to positives\n",
    "        \n",
    "    \"\"\"\n",
    "     for each element \n",
    "     in the set of numbers running from zero to 1-elements of lambda\n",
    "     w is the index of minimum that has the absolute value of the numbber running from 0 to 1-elements\n",
    "     i_mu is a function of intensity in terms of mu where the right side and the left side are put together and sorted\n",
    "     i_mu/=i_mu.max() is normalizing because without it we cannot compare as some parts of the data are too high or too low\n",
    "     plot mu \n",
    "     \n",
    "     \n",
    "     plot left and right as one sampling, before one is without collapsing\n",
    "     assumes that limb darkening is symmetric (doppler shift unaccounting)\n",
    "     \"\"\"   \n",
    "    \n",
    "    plt.legend(title=\"Wavelength (nm)\", loc=\"upper right\",fontsize=8)#Plots and titles the graph, and places it in the upper right     \n",
    "    plt.xlabel(\"mu\") #labels the x-axis as mu\n",
    "    plt.ylabel(\"Normalized Intensity\") #labels the y-axis as Normalized Intensity\n",
    "    plt.xlim(1,mu.min()) #xlimit from 1 to the smallest value of mu \n",
    "    \n",
    "    \n",
    "    plt.savefig(plotname)     \n",
    "    plt.show() #plots the plot\n",
    "    \n",
    "def mu_plot_bands(wavelength, intensity, dr, stretch, plotname, Lambdas, colors):\n",
    "    Nruns=intensity.shape[0]\n",
    "    r=((np.arange(Nruns)-Nruns/2.)/(0.5*Nruns) + dr)*stretch # stretch lets little r be greater than 1\n",
    "    \"\"\"mu_plot_bands is a function that is very similar to the normal mu_plot, the difference is that it takes\n",
    "    bands instead of just wavelengths. Has almost the same attributes. \"\"\"\n",
    "    mu = np.sqrt(1-r**2)\n",
    "    \"\"\" mu is the equation that we need for mu.\n",
    "    mu is then stacked horizontally for both as the right side and the left side \"\"\"\n",
    "    mu = np.hstack((mu[r>0],mu[r<=0]))\n",
    "    for i in range(len(Lambdas)):  #plot several different wavelenghts in different colours \n",
    "        w1=np.argmin(np.abs(wavelength-Lambdas[i][0]))\n",
    "        w2=np.argmin(np.abs(wavelength-Lambdas[i][1]))\n",
    "        i_mu=np.vstack((intensity[r>0, w1:w2+1], intensity[r<=0, w1:w2+1])) #taking right and left hands sides putting them together and sorting them by location on the sun \n",
    "        i_mu = i_mu.sum(1)\n",
    "        i_mu/=i_mu.max()\n",
    "        plt.plot(mu, i_mu, color=colors[i], label=\"{}-{}\".format(*Lambdas[i]))#r values in the same order as the intensity, -1ones to positives\n",
    "        \"\"\"for each element in the set of elements in the new Lambdas (which in this case are the bands, not wavelengths)\n",
    "        w1/w2=creates a range of two wavelengths that we specify to create a band, for example 400-500. \n",
    "        This is how you get bands instead of wavelengths.\n",
    "        Wach column adding intensity in the band, as if integrating over band pass. \n",
    "        Intensity in terms of mu takes the right and left sides putting them together and sorting them by location on the sun\n",
    "        after which it is normalized in order to normalise noise data. \"\"\"\n",
    "    plt.legend(title=\"Wavelength (nm)\", loc=\"upper right\",fontsize=8)    \n",
    "    plt.xlabel(\"mu\") #xlabel as mu \n",
    "    plt.ylabel(\"Normalized Intensity\") #y label as Normalised Intensity\n",
    "    plt.xlim(1,mu.min()) #xlimit from 1 to the smallest value of mu \n",
    "    \n",
    "    \n",
    "    plt.savefig(plotname)     # remove the comment in order to plot the graph and save it \n",
    "    plt.show() #show the graph"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'files is the compilation of all the files/trials that are in\\nthe directory that will be analysed for this project. In this case they all begin with my name and\\nthe date of the experiment. '"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dir = '/Users/VoldemortIsAwesome/Downloads/' \n",
    "\"\"\"Dir establishes the directory from which the \n",
    "read_data obtains the file and reads and breaks it down into wavelengths and intensity. \"\"\"\n",
    "\n",
    "files = glob(dir+'Mohira_160311*.csv') \n",
    "\"\"\"files is the compilation of all the files/trials that are in\n",
    "the directory that will be analysed for this project. In this case they all begin with my name and\n",
    "the date of the experiment. \"\"\"\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "What should dr be?0.1\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYkAAAEPCAYAAAC3NDh4AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\npFJKEiIiUiklCRERqdT/A8B5X00OOAfyAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x105449bd0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Was that good (0) or bad (1)1\n",
      "What should dr be?0.2\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYkAAAEPCAYAAAC3NDh4AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/x+XjlFdLuxA6QAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x105421e50>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Was that good (0) or bad (1)0.1\n",
      "What should dr be?0.1\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYkAAAEPCAYAAAC3NDh4AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\npFJKEiIiUiklCRERqdT/A8B5X00OOAfyAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1058d7450>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Was that good (0) or bad (1)0\n",
      "Mohira, write down: /Users/VoldemortIsAwesome/Downloads/Mohira_160311_trial_1.csv,dr=0.1\n"
     ]
    }
   ],
   "source": [
    "for file in files:\n",
    "    l, I = read_data(file)\n",
    "    \n",
    "    bad = True\n",
    "    while bad:\n",
    "        dr = input(\"What should dr be?\")\n",
    "        plot_raw_data(l,I,dr, False, 'sillyplot.png')\n",
    "        bad = input(\"Was that good (0) or bad (1)\")\n",
    "        \n",
    "    print(\"Mohira, write down: {},dr={}\".format(file,dr))\n",
    "    \"\"\"for each file in the files take the wavelength and the intensity from each trial as \n",
    "    decomposed from read_data function\n",
    "    and estimate dr value for each trial (should store it in a table!!!!) if the estimate for dr is bad,\n",
    "    try again until a functional\n",
    "    dr is obtained. Create a list of dr's to be used below for the actual calculations of mu and mu_bands. \"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "l,I=read_data(files[0]) \n",
    "\"\"\"Wavelength and the intensity that are being read from first trial and stored as wavelength\n",
    "and intensity separately\"\"\"\n",
    "plt.plot(l,I[I.shape[0]/2.]) # plotting the spectrum from the center of the Sun, half way\n",
    "plt.show() #shows the spectrum \n",
    "mu_plot(l,I,0.1,1,\"Blah blah\", [450,520,656.3,700], [\"b\",\"g\",\"m\",\"r\"]) \n",
    "\"\"\"mu plot being actually run. dr is obtained from the function below. \"\"\"\n",
    "mu_plot_bands(l,I,0.1,1,\"Blah blah\", [[400,450],[500,550],[650,700],[800,900]], [\"b\",\"g\",\"r\",'k'])\n",
    "\"\"\"Plots the bands instead of the wavelength, dr is obtained above. Assuming that dr works for all\"\"\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "#make and array that has all values for the dr part, intensity of right wing minus the intensity of the left wing, and then maybe square it in order to gain higher accuracy. Get a function that you can plot against dr. Do some measures and find the minimum. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def notAnotherFunction(wavelength, intensity):\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}