Adityanagraj

class FishModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(input_size, output_size)                # fill this (hint: use input_size & output_size defined above)
        
    def forward(self, xb):
        out = self.linear(xb)                          # fill this
        return out
    
    def training_step(self, batch):

Adityanagraj

dataset = TensorDataset(inputs, targets)
dataset

Adityanagraj

inputs = torch.from_numpy(inputs_array).type(torch.float32)
targets = torch.from_numpy(targets_array).type(torch.float32)

inputs,targets

Adityanagraj

def dataframe_to_arrays(dataframe):
    # Make a copy of the original dataframe
    data1 = data.copy(deep=True)
    # Convert non-numeric categorical columns to numbers
    for col in categorical_cols:
        data1[col] = data1[col].astype('category').cat.codes
    # Extract input & outupts as numpy arrays
    inputs_array = data1[input_cols].to_numpy()
    targets_array = data1[output_cols].to_numpy()
    return inputs_array, targets_array

Adityanagraj

data.shape

Adityanagraj

import torch
import torchvision
import torch.nn as nn
import pandas as pd
import matplotlib.pyplot as plt
import torch.nn.functional as F
from torchvision.datasets.utils import download_url
from torch.utils.data import DataLoader, TensorDataset, random_split

Adityanagraj

#importing all necessary requirements
import pandas as pd
import matplotlib.pyplot as plt
from pywaffle import Waffle
 
#creation of a dataframe
data={'phone': ['Xiaomi', 'Samsung', 'Apple','Nokia','Realme'],
 'stock': [44,12,8,5,3]
 }
df=pd.DataFrame(data)

Adityanagraj

data={‘phone’: [‘Xiaomi’, ‘Samsung’, ‘Apple’,’Nokia’,’Realme’],
‘stock’: [44,12,8,5,3]
}

Adityanagraj

x = torch.arange(1., 10)
x
x.unfold(0,2,1)

Adityanagraj

x = torch.arange(1., 10)
x
x.unfold(-1,1,3)