Fix typos

Want to find relationships between explanatory variables.

notebooks/11_investigate.ipynb

@@ -0,0 +1,261 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Investigate "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup notebook\n",
+    "Import our required packages and set default plotting options."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Enable autoreloading of our modules. \n",
+    "# Most of the code will be located in the /src/ folder, \n",
+    "# and then called from the notebook.\n",
+    "%matplotlib inline\n",
+    "%reload_ext autoreload\n",
+    "%autoreload"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.core.debugger import set_trace\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import decimal\n",
+    "import plotly\n",
+    "import plotly.graph_objs as go\n",
+    "import plotly.plotly as py\n",
+    "import plotly.tools as tls\n",
+    "import plotly.figure_factory as ff\n",
+    "from plotly import tools\n",
+    "import plotly.io as pio\n",
+    "from scipy import stats\n",
+    "import math\n",
+    "import matplotlib\n",
+    "from matplotlib import cm\n",
+    "import colorlover as cl\n",
+    "from tqdm import tqdm_notebook\n",
+    "from ipywidgets import widgets, Output\n",
+    "from IPython.display import display, clear_output, Image, HTML\n",
+    "from scipy import stats\n",
+    "from sklearn.metrics import confusion_matrix\n",
+    "import matplotlib.pyplot as plt\n",
+    "from matplotlib.ticker import MultipleLocator\n",
+    "from matplotlib.lines import Line2D\n",
+    "from cycler import cycler\n",
+    "from scipy.interpolate import interp1d\n",
+    "from pandas.api.types import CategoricalDtype"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Matplot lib default settings\n",
+    "plt.rcParams[\"figure.figsize\"] = (10,6)\n",
+    "plt.rcParams['axes.grid']=True\n",
+    "plt.rcParams['grid.alpha'] = 0.5\n",
+    "plt.rcParams['grid.color'] = \"grey\"\n",
+    "plt.rcParams['grid.linestyle'] = \"--\"\n",
+    "plt.rcParams['axes.grid']=True\n",
+    "\n",
+    "# https://stackoverflow.com/a/20709149\n",
+    "# matplotlib.rcParams['text.usetex'] = True\n",
+    "\n",
+    "matplotlib.rcParams['text.latex.preamble'] = [\n",
+    "       r'\\usepackage{siunitx}',   # i need upright \\micro symbols, but you need...\n",
+    "       r'\\sisetup{detect-all}',   # ...this to force siunitx to actually use your fonts\n",
+    "       r'\\usepackage{helvet}',    # set the normal font here\n",
+    "       r'\\usepackage{amsmath}',\n",
+    "       r'\\usepackage{sansmath}',  # load up the sansmath so that math -> helvet\n",
+    "       r'\\sansmath',              # <- tricky! -- gotta actually tell tex to use!\n",
+    "]  "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import data\n",
+    "Import our data from the `./data/interim/` folder and load it into pandas dataframes. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def df_from_csv(csv, index_col, data_folder='../data/interim'):\n",
+    "    print('Importing {}'.format(csv))\n",
+    "    return pd.read_csv(os.path.join(data_folder,csv), index_col=index_col)\n",
+    "\n",
+    "df_waves = df_from_csv('waves.csv', index_col=[0, 1])\n",
+    "df_tides = df_from_csv('tides.csv', index_col=[0, 1])\n",
+    "df_profiles = df_from_csv('profiles.csv', index_col=[0, 1, 2])\n",
+    "df_sites = df_from_csv('sites.csv', index_col=[0])\n",
+    "df_sites_waves = df_from_csv('sites_waves.csv', index_col=[0])\n",
+    "df_profile_features_crest_toes = df_from_csv('profile_features_crest_toes.csv', index_col=[0,1])\n",
+    "\n",
+    "# Note that the forecasted data sets should be in the same order for impacts and twls\n",
+    "impacts = {\n",
+    "    'forecasted': {\n",
+    "    'postintertidal_slope_sto06': df_from_csv('impacts_forecasted_postintertidal_slope_sto06.csv', index_col=[0]),\n",
+    "    'postmean_slope_sto06': df_from_csv('impacts_forecasted_postmean_slope_sto06.csv', index_col=[0]),\n",
+    "    'preintertidal_slope_sto06': df_from_csv('impacts_forecasted_preintertidal_slope_sto06.csv', index_col=[0]),\n",
+    "    'premean_slope_sto06': df_from_csv('impacts_forecasted_premean_slope_sto06.csv', index_col=[0]),\n",
+    "        },\n",
+    "    'observed': df_from_csv('impacts_observed.csv', index_col=[0])\n",
+    "    }\n",
+    "\n",
+    "twls = {\n",
+    "    'forecasted': {\n",
+    "    'postintertidal_slope_sto06': df_from_csv('twl_postintertidal_slope_sto06.csv', index_col=[0,1]),\n",
+    "    'postmean_slope_sto06': df_from_csv('twl_postmean_slope_sto06.csv', index_col=[0,1]),\n",
+    "    'preintertidal_slope_sto06': df_from_csv('twl_preintertidal_slope_sto06.csv', index_col=[0,1]),\n",
+    "    'premean_slope_sto06': df_from_csv('twl_premean_slope_sto06.csv', index_col=[0,1]),\n",
+    "    }\n",
+    "}\n",
+    "print('Done!')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Sec1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create df with all our data\n",
+    "df = impacts['observed'].merge(df_sites_waves,left_index=True,right_index=True)\n",
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import seaborn as sns\n",
+    "sns.set(style=\"white\")\n",
+    "g = sns.pairplot(\n",
+    "    data=df,\n",
+    "    hue='storm_regime',\n",
+    "    dropna=True,\n",
+    "    palette={\n",
+    "        'swash': 'blue',\n",
+    "        'collision': 'orange',\n",
+    "        'overwash': 'red'\n",
+    "    },\n",
+    "    vars=['beta_prestorm_mean',\n",
+    "          'beta_poststorm_mean',\n",
+    "          'beta_diff_mean',\n",
+    "          'swash_pct_change',\n",
+    "          'df_width_msl_change_m',\n",
+    "          'df_width_msl_change_pct',\n",
+    "          'Exscum'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "g.savefig('11_pairplot.png')"
+   ]
+  }
+ ],
+ "metadata": {
+  "hide_input": false,
+  "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": "3.6.6"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

src/analysis/observed_storm_impacts.py

@@ -231,8 +231,8 @@ def overwrite_impacts(df_observed_impacts, df_raw_features):
     df_observed_impacts.update(df_overwritten_impacts)
 
     # Replace 'none' with nan
-    df_overwritten_impacts.loc[
+    df_observed_impacts.loc[
-        df_overwritten_impacts.storm_regime == "unknown", "storm_regime"
+        df_observed_impacts.storm_regime == "unknown", "storm_regime"
     ] = np.nan
     return df_observed_impacts
 
@@ -343,8 +343,8 @@ def create_observed_impacts(
         ele=0,
         col_name="width_msl_poststorm",
     )
-    df_width_msl_change_m = (df_width_msl_poststorm - df_width_msl_prestorm).rename('df_width_msl_change_m')
+    df_width_msl_change_m = (df_width_msl_poststorm - df_width_msl_prestorm).rename('width_msl_change_m')
-    df_width_msl_change_pct = (df_width_msl_change_m / df_width_msl_prestorm * 100).rename('df_width_msl_change_pct')
+    df_width_msl_change_pct = (df_width_msl_change_m / df_width_msl_prestorm * 100).rename('width_msl_change_pct')
 
     # Join beach width change onto observed impacts dataframe
     df_observed_impacts = pd.concat(