This is an attempt to try to predict stock prices in the future. I want to explore and compare the results between LSTM and other modeling algorithms. I also want to explore the possibilities of optimizing LSTMs. Analysis done in python IDLE 3.5.3. Please refer to the blank and blank for the complete project and report details.
- Project Proposal: Detailing project motivation
- Project Report: Detailing feature engineering and modeling excercise
- Feature Engineering: Code for feature engineering
- Main Model Optimization & Selection: Code for model optimization using GridSearchCV
- Visualizations: Folder contains all visualizations for the project
- Data Dictionary: Data dictionary
- Model Summary: Selecting optimized modeling algorithm
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import visuals as vs #from one of the MLND project. Was useful in visualizing PCA
from time import gmtime, strftime, time
import warnings
from scipy import stats
from scipy.special import boxcox1p
from scipy.stats import norm, skew
from sklearn.preprocessing import LabelEncoder
from sklearn.decomposition import PCA
from sklearn.linear_model import ElasticNet, Lasso
from sklearn.tree import DecisionTreeRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor, AdaBoostRegressor
from sklearn.neural_network import MLPRegressor
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.wrappers.scikit_learn import KerasRegressor
import xgboost as xgb
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import RobustScaler
from sklearn.model_selection import KFold, cross_val_score, train_test_split, ShuffleSplit, GridSearchCV
from sklearn.metrics import mean_squared_error
from Feature_Engineering import data_wrangle