diff --git a/TDA_Prediction.ipynb b/TDA_Prediction.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..6af9c03d8502abf3b19cd242809e5888ebfa5f84
--- /dev/null
+++ b/TDA_Prediction.ipynb
@@ -0,0 +1,160 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "<h1><center>Prediction using Topological Data Analysis</center></h1>"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Give brief overview of notebook's purpose.\n",
+ "Also maybe add cool picture."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from Topological_ML import TDA_Prediction as tdap\n",
+ "from sklearn.datasets import fetch_california_housing\n",
+ "import pandas as pd\n",
+ "import numpy as np"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 45,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "cal_housing = fetch_california_housing()\n",
+ "\n",
+ "def numpy_to_pandas(sklearn_data):\n",
+ " df = pd.DataFrame(data = sklearn_data.data, columns = sklearn_data.feature_names)\n",
+ " df['response'] = pd.Series(sklearn_data.target)\n",
+ " return df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 50,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df = numpy_to_pandas(cal_housing)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 66,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Shape : (20640, 9)\n",
+ "Head -- \n",
+ " MedInc HouseAge AveRooms AveBedrms Population AveOccup Latitude \\\n",
+ "0 8.3252 41.0 6.984127 1.023810 322.0 2.555556 37.88 \n",
+ "1 8.3014 21.0 6.238137 0.971880 2401.0 2.109842 37.86 \n",
+ "2 7.2574 52.0 8.288136 1.073446 496.0 2.802260 37.85 \n",
+ "3 5.6431 52.0 5.817352 1.073059 558.0 2.547945 37.85 \n",
+ "4 3.8462 52.0 6.281853 1.081081 565.0 2.181467 37.85 \n",
+ "\n",
+ " Longitude target \n",
+ "0 -122.23 4.526 \n",
+ "1 -122.22 3.585 \n",
+ "2 -122.24 3.521 \n",
+ "3 -122.25 3.413 \n",
+ "4 -122.25 3.422 \n",
+ "Describe : MedInc HouseAge AveRooms AveBedrms Population \\\n",
+ "count 20640.000000 20640.000000 20640.000000 20640.000000 20640.000000 \n",
+ "mean 3.870671 28.639486 5.429000 1.096675 1425.476744 \n",
+ "std 1.899822 12.585558 2.474173 0.473911 1132.462122 \n",
+ "min 0.499900 1.000000 0.846154 0.333333 3.000000 \n",
+ "25% 2.563400 18.000000 4.440716 1.006079 787.000000 \n",
+ "50% 3.534800 29.000000 5.229129 1.048780 1166.000000 \n",
+ "75% 4.743250 37.000000 6.052381 1.099526 1725.000000 \n",
+ "max 15.000100 52.000000 141.909091 34.066667 35682.000000 \n",
+ "\n",
+ " AveOccup Latitude Longitude target \n",
+ "count 20640.000000 20640.000000 20640.000000 20640.000000 \n",
+ "mean 3.070655 35.631861 -119.569704 2.068558 \n",
+ "std 10.386050 2.135952 2.003532 1.153956 \n",
+ "min 0.692308 32.540000 -124.350000 0.149990 \n",
+ "25% 2.429741 33.930000 -121.800000 1.196000 \n",
+ "50% 2.818116 34.260000 -118.490000 1.797000 \n",
+ "75% 3.282261 37.710000 -118.010000 2.647250 \n",
+ "max 1243.333333 41.950000 -114.310000 5.000010 \n",
+ "None\n"
+ ]
+ }
+ ],
+ "source": [
+ "def descriptive_statistic(df, n):\n",
+ " \"\"\"\n",
+ " Provides brief descriptive statistics on dataset. \n",
+ " Takes dataframe as input.\n",
+ " \"\"\"\n",
+ " print(\"Shape : \", df.shape)\n",
+ " print(\"Head -- \\n\", df.head(n))\n",
+ " print(\"Describe : \", df.describe())\n",
+ " \n",
+ "descriptive_statistic(df, 5)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def test_srt_rt1():\n",
+ " assert tdap.mysqrt(-4) == 2\n",
+ " return\n",
+ "\n",
+ "def test_srt_rt2():\n",
+ " assert tdap.mysqrt(4) == 2\n",
+ " return\n",
+ "\n"
+ ]
+ }
+ ],
+ "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
+}
diff --git a/Topological_ML/TDA_Prediction.py b/Topological_ML/TDA_Prediction.py
index bd9c6e29e6784898059c36e0dc382088efe91ba8..147594cedfb197bd34483908ab891469207cac9e 100644
--- a/Topological_ML/TDA_Prediction.py
+++ b/Topological_ML/TDA_Prediction.py
@@ -1,28 +1,23 @@
-def dataload():
+def numpy_to_pandas(sklearn_data):
"""
- upload toy datasets from scikit-learn
+ Converts scikit-learn numpy data into pandas dataframe.
+ Input: name of dataframe
+ Output: pandas dataframe
"""
- data = None
- return data
+ df = pd.DataFrame(data = sklearn_data.data, columns = sklearn_data.feature_names)
+ df['response'] = pd.Series(sklearn_data.target)
+ return df
-def datafetch(file_name):
- """
- upload real world datasets from scikit-learn
- """
- data = None
- print("reading data from:", file_name)
- return data
-
-def descriptive_statistic(df):
+def descriptive_statistic(df, n):
"""
Provides brief descriptive statistics on dataset.
- Takes dataframe as input.
+ Input: df = dataframe
+ n = the first n rows of the dataframe
+ Output: shape, head, and descriptive statistics of dataframe
"""
- print("Type : ", None, "\n\n")
- print("Shape : ", None)
- print("Head -- \n", None)
- print("\n\n Tail -- \n", None)
- print("Describe : ", None)
+ print("Shape : ", df.shape)
+ print("Head -- \n", df.head(n))
+ print("Describe : ", df.describe())
def model_selection(df):
"""
@@ -61,4 +56,11 @@ def accuracy_metrics(fit, MSE):
d['BIC'] = None
d['PRESS'] = None
d['Cp']= None
- return d
\ No newline at end of file
+ return None
+
+
+def mysqrt(n):
+ if n < 0:
+ n = 1.5*abs(n)
+ sqrt1 = n**(1/2)
+ return sqrt1
\ No newline at end of file