aniruddha27

# Data generator

# For train data
train_datagen = ImageDataGenerator(rescale=1.0/255,
                                   rotation_range=10,
                                   width_shift_range=0.2,
                                   height_shift_range=0.2,
                                   horizontal_flip=True,
                                   brightness_range=[0.4,0.9],
                                   zoom_range=0.2)

aniruddha27

# Model architechture
model = Sequential()

model.add(Conv2D(32, (3, 3), input_shape=(224, 224, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3), activation='relu'))

aniruddha27

from keras.models import Sequential
from keras.layers import Dropout, Flatten, Dense, Conv2D, MaxPooling2D, BatchNormalization
from keras.optimizers import SGD
import keras
from sklearn.model_selection import train_test_split
import cv2

aniruddha27

sort = sorted(prep_dict.items(), key = lambda d:(d[1],d[0]), reverse=True)
sort[:10]

aniruddha27

# Folder path
folders = glob.glob('./UNGD/UNGDC 1970-2018/Converted sessions/Session*')

# Dataframe
df = pd.DataFrame(columns={'Country','Speech','Session','Year'})

# Read speeches by India
i = 0 
for file in folders:
    

aniruddha27

# separate noun, preposition and noun

prep_dict = dict()
dis_dict = dict()
dis_list = []

# iterating over all the sentences
for i in range(len(df_show3)):
    
    # sentence containing the output

aniruddha27

# select non-empty outputs
df_show3 = pd.DataFrame(columns=df_rule3_all.columns)

for row in range(len(df_rule3_all)):
    
    if len(df_rule3_all.loc[row,'Output'])!=0:
        df_show3 = df_show3.append(df_rule3_all.loc[row,:])

# reset the index
df_show3.reset_index(inplace=True)

aniruddha27

# create a df containing sentence and its output for rule 3
row_list = []

# df2 contains all the sentences from all the speeches
for i in range(len(df2)):
    
    sent = df2.loc[i,'Sent']
    year = df2.loc[i,'Year']
    output = rule3(sent)
    dict1 = {'Year':year,'Sent':sent,'Output':output}

aniruddha27

# create a df containing sentence and its output for rule 3
row_list = []

for i in range(len(df3)):
    
    sent = df3.loc[i,'Sent']
    year = df3.loc[i,'Year']
    
    # rule
    output = rule3(sent)

aniruddha27

# create a df containing sentence and its output for modified rule 1
row_list = []

# df2 contains all the sentences from all the speeches
for i in range(len(df2)):
    
    sent = df2.loc[i,'Sent']
    year = df2.loc[i,'Year']
    output = rule1_mod(sent)
    dict1 = {'Year':year,'Sent':sent,'Output':output}