ChristopherDaigle

from sklearn.linear_model import LinearRegression, Ridge
from sklearn.model_selection import train_test_split

X = df_final.drop(['vote_average', 'release_date'], axis=1)
y = df_final['vote_average']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

lm_model = LinearRegression(normalize=True)
r_model = Ridge(normalize=True)

ChristopherDaigle

from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
from sklearn.ensemble import AdaBoostClassifier, RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import fbeta_score, accuracy_score

models = {'log_model': LogisticRegression(random_state=0),
          'log_cv_model': LogisticRegressionCV(),
          'ab_model':AdaBoostClassifier(random_state=0),
          'rf_model': RandomForestClassifier(random_state=0),

ChristopherDaigle

from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler(feature_range=(0, 1))
numerical = ['orig_title_len', 'overview_len', 'tagline_len', 'title_len',
             'popularity', 'runtime', 'vote_average', 'vote_count']

df_impute_log_minmax = pd.DataFrame(data = df_1_impute_fill).copy()
df_impute_log_minmax[numerical] = scaler.fit_transform(df_1_impute_fill[numerical])

# Preserve final df transformation:
df_impute_transformed = df_impute_log_minmax

ChristopherDaigle

from sklearn.impute import KNNImputer

imputer = KNNImputer(n_neighbors=int(round(np.sqrt(df_1.shape[0]))))

df_1.reset_index(inplace = True, drop = True)
impute_df = df_1.drop(columns='release_date')
impute_df_filled = imputer.fit_transform(X=impute_df)

imputed_cols = list(df_1.drop(columns='release_date').columns)
df_impute = pd.DataFrame(data=impute_df_filled, columns=imputed_cols)

ChristopherDaigle

from sklearn.linear_model import LinearRegression, Ridge
from sklearn.model_selection import train_test_split

X = df_final.drop(['revenue', 'release_date'], axis=1)
y = df_final['revenue']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

lm_model = LinearRegression(normalize=True)
r_model = Ridge(normalize=True)

ChristopherDaigle

from sklearn.linear_model import LinearRegression, Ridge
from sklearn.model_selection import train_test_split

X = df_1.drop(['revenue', 'above_ave_rev_yr', 'original_language', 'original_title', 'overview', 'release_date', 'status', 'tagline', 'title'], axis=1)
y = df_1['revenue']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

lm_model = LinearRegression(normalize=True)
r_model = Ridge(normalize=True)

ChristopherDaigle

from lxml import html  
import requests
from time import sleep
import json
import argparse
from collections import OrderedDict
from time import sleep

def parse(ticker):
	url = "http://finance.yahoo.com/quote/%s?p=%s"%(ticker,ticker)

ChristopherDaigle

ChristopherDaigle

#!/usr/bin/env python
#-*- coding: utf-8 -*-

# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of