adding time series files.

comparing_machine_learning_algorithms.py

@@ -9,7 +9,8 @@
 from sklearn.naive_bayes import GaussianNB
 from sklearn.svm import SVC
 # load dataset
-url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv"
+#url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv"
+url = "pima-indians-diabetes-data.csv"
 names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
 dataframe = pandas.read_csv(url, names=names)
 array = dataframe.values
@@ -44,4 +45,4 @@
 ax = fig.add_subplot(111)
 plt.boxplot(results)
 ax.set_xticklabels(names)
-plt.show()
+plt.show()

nltk_practice.py

@@ -0,0 +1,25 @@
+from nltk import sent_tokenize
+from nltk.tokenize import word_tokenize
+
+text = "Success is not final. Failure is not fatal. It is the courage to continure that counts."
+
+sent_tokens = sent_tokenize(text)
+
+print(sent_tokens)
+
+for sentence in sent_tokens:
+    print(sentence)
+
+sent = "Let's see how the tokenizer split's this!"
+word_tokens = word_tokenize(sent)
+print(word_tokens)
+from nltk.tokenize import TreebankWordTokenizer, WordPunctTokenizer, WhitespaceTokenizer
+tree_tokenizer = TreebankWordTokenizer()
+word_punct_tokenizer = WordPunctTokenizer()
+white_space_tokenizer = WhitespaceTokenizer()
+word_tokens = tree_tokenizer.tokenize(sent)
+print(word_tokens)
+word_tokens = word_punct_tokenizer.tokenize(sent)
+print(word_tokens)
+word_tokens = white_space_tokenizer.tokenize(sent)
+print(word_tokens)

replacement_list_comparer.py

@@ -42,6 +42,8 @@ def compare(self):
             if old_item in self.new_list:
                 # YoY match
                 print("FOUND EXACT MATCH: {}".format(old_item))
+                #translation[old_item] = old_item
+
                 continue
             elif any(substring for substring in self.json_translation_dict_keys if substring in old_item ):
                 answer = self.search_for_common_replacements_match(old_item)

stock_market_prediction_minute.py

@@ -0,0 +1,86 @@
+# https://medium.com/mlreview/a-simple-deep-learning-model-for-stock-price-prediction-using-tensorflow-30505541d877
+
+import pandas as pd
+import matplotlib.pyplot as plt
+
+import tensorflow as tf
+
+# import data
+# 
+# data was already cleaned and prepared, 
+# meaning missing stock and index prices 
+# were LOCF'ed (last observation carried 
+# forward), so that the file did not 
+# contain any missing values
+data = pd.read_csv('./sp500/data_stocks.csv')
+
+# drop data variable
+data = data.drop(['DATE'], 1)
+
+# dimensions of dataset
+n = data.shape[0]
+p = data.shape[1]
+
+plt.plot(data['SP500'])
+plt.show()
+
+
+# make data a numpy array
+data = data.values
+
+
+
+# training and test data 
+train_start = 0
+train_end = int(np.floor(0.8*n))
+
+test_start = train_end
+test_end = n
+
+data_train = data[np.arange(train_start, train_end), :]
+data_test = data[np.arange(test_start, test_end), :]
+
+
+# scale data
+from sklearn.preprocessing import MinMaxScaler
+scaler = MinMaxScaler()
+data_train = scaler.fit_transform(data_train)
+data_test = scaler.transform(data_test)
+
+# build X and Y
+X_train = data_train[:, 1:]
+Y_train = data_train[:, 0]
+X_test = data_test[:, 1:]
+Y_test = data_test[:, 0]
+
+
+# placeholder
+X = tf.placeholder(dtype=tf.float32, shape=[None, n_stocks])
+Y = tf.placeholder(dtype=tf.float32, shape=[None])
+
+# model architecture parameters
+n_stocks = 500
+n_neurons_1 = 1024
+n_neurons_2 = 512
+n_neurons_3 = 256
+n_neurons_4 = 128
+n_target = 1
+
+# Layer 1: variables for hidden weights and biases
+W_hidden_1 = tf.Variable(weight_initializer([n_stocks, n_neurons_1]))
+bias_hidden_1 = tf.Variable(bias_initializer([n_neurons_1]))
+
+# Layer 2: Variables for hidden weights and biases
+W_hidden_2 = tf.Variable(weight_initializer([n_neurons_1, n_neurons_2]))
+bias_hidden_2 = tf.Variable(bias_initializer([n_neurons_2]))
+# Layer 3: Variables for hidden weights and biases
+W_hidden_3 = tf.Variable(weight_initializer([n_neurons_2, n_neurons_3]))
+bias_hidden_3 = tf.Variable(bias_initializer([n_neurons_3]))
+# Layer 4: Variables for hidden weights and biases
+W_hidden_4 = tf.Variable(weight_initializer([n_neurons_3, n_neurons_4]))
+bias_hidden_4 = tf.Variable(bias_initializer([n_neurons_4]))
+# Output layer: Variables for output weights and biases
+W_out = tf.Variable(weight_initializer([n_neurons_4, n_target]))
+bias_out = tf.Variable(bias_initializer([n_target]))
+
+

time_series_stock_basic.py

@@ -0,0 +1,36 @@
+# https://www.analyticsvidhya.com/blog/2018/10/predicting-stock-price-machine-learningnd-deep-learning-techniques-python/
+
+# import packages
+import pandas as pd
+import numpy as np
+
+# to plot within notebook
+import matplotlib.pyplot as plt
+
+# setting figure size
+from matplotlib.pylab import rcParams
+rcParams['figure.figsize'] = 20,10
+
+# for normalizing data
+from sklearn.preprocessing import MinMaxScaler
+scaler = MinMaxScaler(feature_range=(0,1))
+
+# read the file
+df = pd.read_csv('NSE-TATAGLOBAL11.csv')
+
+# print the head
+print(df.head())
+
+
+# setting index as date
+df['Date'] = pd.to_datetime(df.Date, format='%Y-%m-%d')
+df.index = df['Date']
+
+# plot
+plt.figure(figsize=(16,8))
+plt.plot(df['Close'], label='Close Price History')
+plt.show()
+
+
+
+