added new functions

Topological_ML/TDA_Prediction.py

+from Topological_ML import TDA_Prediction as tdap
+from sklearn.datasets import fetch_california_housing
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+import kmapper as km
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import sklearn
+from sklearn import ensemble
+
 def numpy_to_pandas(sklearn_data):
     """
     Converts scikit-learn numpy data into pandas dataframe.
@@ -8,16 +19,17 @@ def numpy_to_pandas(sklearn_data):
     df['response'] = pd.Series(sklearn_data.target)
     return df
 
-def descriptive_statistic(df, n):
+def data_summary(df, n):
     """
     Provides brief descriptive statistics on dataset. 
-    Input: df = dataframe 
-           n = the first n rows of the dataframe
-    Output: shape, head, and descriptive statistics of dataframe
+    Input: name of dataframe
+    Output: dictionary 
     """
-    print("Shape : ", df.shape)
-    print("Head -- \n", df.head(n))
-    print("Describe : ", df.describe())
+    d = dict()
+    d['head'] = df.head(n)
+    d['shape'] = df.shape
+    #d['missing values'] = df.isna().sum()
+    return d
     
 def model_selection(df):
     """
@@ -38,29 +50,47 @@ def MSE_fit(fit):
     MSE = None
     return MSE
 
-def accuracy_metrics(fit, MSE):
+def accuracy_metrics(fit, MSE, n, k):
     """
     This function is used for model validation. It returns a dictionary
     of several regression model accuracy metrics. Its inputs are a fitted model
     and the MSE of the fitted model.
     """
     d = dict()
-    sumObj = None
-    SSE = None
+    y_hat = model.predict(X)
+    resid = y - y_hat
+    SSE = sum(resid**2)
     n = None
     p = None
     pr = None
     d['R2'] = None
     d['R2ad'] = None
-    d['AIC'] = None
-    d['BIC'] = None
+    d['AIC'] = 2*k - 2*ln(SSE)
+    d['BIC'] = n*ln(SSE/n) + k*ln(n)
     d['PRESS'] = None
     d['Cp']= None
     return None
 
+def linear_regression(x, y):
+    """
+    Ordinary least squares Linear Regression.
+    input: x = independent variables
+           y = dependent variable
+    output: R^2
+    """
+    model = LinearRegression()
+    model.fit(x, y)
+    return model.score(x ,y)
 
-def mysqrt(n):
-    if n < 0:
-        n = 1.5*abs(n)
-    sqrt1 = n**(1/2)
-    return sqrt1
\ No newline at end of file
+def lens_1d(X, rs, v):
+    """
+    input:
+    output:
+    """
+    model = sklearn.ensemble.IsolationForest(random_state = rs)
+    model.fit(X)
+    lens1 = model.decision_function(X).reshape((X.shape[0], 1))
+    mapper = km.KeplerMapper(verbose = v)
+    lens2 = mapper.fit_transform(X, projection="l2norm")
+    lens = np.c_[lens1, lens2]
+    return lens
\ No newline at end of file