AVJdataminer

Fill_NA<-function(x,home,modelpath){
  setwd(modelpath)
  if(nrow(x)<1){x<-read.csv(list.files(pattern = "indata_file.csv"))}
  #split into numeric and non-numeric
  require(PCAmixdata)
  ds=splitmix(x)

  impute.med <- function(x) {
    z <- median(x, na.rm = TRUE)
    x[is.na(x)] <- z

AVJdataminer

1BuUfzs5npAQuTKEvynYNkA5eRDpu3WTL5.id" is my Blockstack ID. https://onename.com/1BuUfzs5npAQuTKEvynYNkA5eRDpu3WTL5

AVJdataminer

import datetime

def time_stamp(df,time_col):
    df[time_col] = pd.to_datetime(df[time_col])
    df["year"] = df[time_col].dt.year
    df["month"] =  df[time_col].dt.month
    df["day"] = df[time_col].dt.day
    df['day_of_yr']=df[time_col].dt.strftime('%j').astype(int)
time_stamp(df,"Latest Launch")

AVJdataminer

dfo=df.select_dtypes(include=['object']) # select object type columns
df = pd.concat([df.drop(dfo, axis=1), pd.get_dummies(dfo)], axis=1)

AVJdataminer

from sklearn.model_selection import train_test_split
df=df.dropna()
X=df.drop(['4-year resale value'], axis=1)
y=df[['4-year resale value']]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=1)

from sklearn import preprocessing
import numpy as np
scaler = preprocessing.StandardScaler().fit(X_train)
X_scaled=scaler.transform(X_train) 

AVJdataminer

import itertools
import numpy as np
import matplotlib.pyplot as plt

from sklearn import svm, datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix

def plot_confusion_matrix(cm, classes,
                          normalize=False,

AVJdataminer

import sklearn.decomposition
pca = sklearn.decomposition.PCA()
pca.fit(X)
variances = pca.explained_variance_ratio_
def select_n_components(var_ratio, goal_var: float) -> int:
    total_variance = 0.0
    n_components = 0
    # For the explained variance of each feature:
    for explained_variance in var_ratio:
        # Add the explained variance to the total

AVJdataminer

filelist = list.files(pattern = ".*.txt")
datalist = lapply(filelist, function(x)read.table(x, header=T)) 

#assuming the same header/columns for all files
datafr = do.call("rbind", datalist)

AVJdataminer

def ext_date(df, column):
    df[column] = pd.to_datetime(df[column],format = "%Y-%m-%d")
    df[column] = df[column].dt.strftime('%Y%m%d')

AVJdataminer

from datetime import datetime,timedelta
def dt_splitter(date_col, X, y, test_size):
        xw_date=pd.DataFrame(X).merge(date_col,left_index=True, right_index=True)
        ad = (max(xw_date.date)- min(xw_date.date)).days*test_size
        split_date = min(xw_date.date) + timedelta(days=ad)
        X_train = xw_date.loc[xw_date['date'] <= split_date].drop(['date'], axis=1).values
        X_test = xw_date.loc[xw_date['date'] > split_date].drop(['date'], axis=1).values
        yw_date=pd.DataFrame(y).merge(date_col,left_index=True, right_index=True)
        y_train=yw_date.loc[yw_date['date'] <= split_date].drop(['date'], axis=1).values
        y_test=yw_date.loc[yw_date['date'] > split_date].drop(['date'], axis=1).values